land use analysis case study

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

5 Land-Use and Transportation Modeling I: Land-Use Analysis

Chapter overview.

Chapter 5 delves into various categories of land-use analysis, focusing on the appropriate allocation of land for diverse activities within urban and regional areas. The chapter outlines the steps involved in land-use modeling, dedicating a significant portion to land-use suitability analysis and the essential spatial analysis skills in urban planning. The chapter provides a summary about regional context analysis, community opportunities analysis, demographic and economic interpretation, natural resources and soil analysis, and cultural resources analysis, all of which are important analyses before performing suitability analysis. Next, the chapter introduces the necessary steps to execute these analyses and provides insights into the most commonly employed land-use classifications in practice. In the concluding section, a case study is presented to illustrate the suitability modeling process along with utilizing land-use database sources and mapping techniques.

Learning Objectives

• Understand how to approach land-use modeling step by step and define the important context-based information needed for land-use modeling.
• Describe the general procedure for land-use suitability analysis, and relate it to other planning undertakings and attempts.
• Apply land-use suitability analysis step by step and interpret its results.
• Summarize and compare various land-use classification systems.
• Compare different land-use records to each other using different techniques in GIS environment.

Introduction

In the preceding chapters, we explored how urban areas are shaped by factors like mobility, accessibility, and travel patterns and how the interaction between land use and transportation can alter the spatial structure of cities and regions. This chapter zooms in on a more detailed examination of land-use planning and analysis, presenting the appropriate methods for allocating land within urban and regional areas to accommodate various activities.

Begin with the fundamental question: what activities are occurring where in a city or region? The goal of such queries is the understanding of diverse activity requirements for land and the assessment of whether a piece of land is suitable for a particular activity.

Land use, as defined by Burley (1961), encompasses both land cover and land utilization. Land cover pertains to the surface of the land, including natural elements like vegetation and soil, as well as human-made features such as infrastructure. On the other hand, land utilization refers to the structures, actions, or activities taking place on the land, as explained by Anderson (1976). In practical terms, envision the planning commission in your city deciding to allocate more land to meet the community’s growing needs. This may involve identifying suitable activities for vacant land or redeveloping parcels. The future land-use maps in the municipal comprehensive plan reflect policy decisions, community vision, and input from citizens and stakeholders.

Drawing from various academic works and practices of planning authorities, several analysis techniques are employed to derive recommendations from raw data in land-use analysis. Key primary data for initiating this analysis include:

• the location of the land by a spatial coordination system;
• existing activities on developed land;
• environmental and natural features including surface and subsurface characteristics;
• density of activity on the land;
• ownership information;
• price of the land; and
• existing infrastructure, such as transportation and utility facilities.

Land-use planning and analysis become critical tasks when a community requires additional land and infrastructure for growth. Urban land development involves various stakeholders, including institutional entities, owners, developers, bankers, and local or state governments, each driven by different motives such as market demands, community needs, and the pursuit of a high-quality and sustainable built environment. Considering the influence of these diverse actors is essential when analyzing and making recommendations for land development in urban areas.

Land-use analysis primarily focuses on the current land use, existing development patterns, compliance with federal, state, and local regulations, proposed development patterns, public input, and measurable objectives for implementation (Wang & Hofe, 2020). Land use activities are broadly classified as residential, occupational, or other (non-residential and non-employment). Properly classifying land parcels based on characteristics, location, and intended use ensures effective and efficient land utilization while adhering to relevant regulations or guidelines. In the United States, the externalities of low-density suburban sprawl have heightened pressure on land and resources. Conversely, in developing countries, limited land availability coupled with rapid population growth has accelerated urbanization and development. Recognizing current and past global trends underscores the critical importance of meticulous land-use planning and analysis.

Land-use analysis major considerations

As previously mentioned, the analysis of land-use allocation in an urban setting demands careful consideration of multiple factors. Effectively conducting this analysis involves taking into account various types of data. The following section offers a succinct overview of different techniques intended for analyzing the diverse data types necessary for various levels of spatial analysis. For more in-depth information on the subject, please consult the “Land Use Resource Guide” provided by the Center for Land Use Education at the University of Wisconsin-Stevens Point. For a more detailed exploration of this topic, please refer to the “Land Use Resource Guide” from the Center for Land Use Education at the University of Wisconsin-Stevens Point. This section draws liberally from the Guide’s Chapter 4, “Land Use Analysis,” originally crafted to guide planners in formulating the land use element of a comprehensive plan.

Regional context analysis

Regional context analysis involves identifying and assessing the surroundings of a community. This is crucial because no context exists in isolation, and the surrounding environment significantly influences future land-use development. The regional context encompasses statewide natural features, economic development efforts, transportation locations and decisions, as well as the plans and actions of nearby communities and other agencies (Haines et al., 2005). For instance, economic growth and increased employment in one community can impact housing needs in adjacent areas. Major regional forces affecting a community should always be considered in land-use planning.

Community opportunities analysis

Community opportunities analysis helps in understanding and determining how opportunities influence future land use. The goal is to allocate sufficient land to capitalize on identified opportunities. For instance, in urban areas, it is crucial to identify opportunities that can enhance economic viability downtown or improve the quality of life in neighborhoods, such as implementing waste treatment systems. These opportunities should be prioritized and specified in future land-use plans (Haines et al., 2005).

Demographic and economic data interpretation

The influence of socio-economic factors on future land use is undeniable. Collecting data on population and job trends helps in determining the mutual impact of these developments. To make informed decisions about the future of land-use patterns, it is essential to gather data on factors such as population growth, age levels, workforce size and skills, and economic activities (Haines et al., 2005).

Natural resources and soil analysis

Natural features, conditions, and resources contribute to the character of a community. Including this information in suitability analysis guides decisions about the type and location of development. This analysis should collect information about various kinds of soils, such as agricultural soil and unsuitable soil for development, as well as the location of underground waters, basins, natural preserves, parks, and archaeological sites. Understanding natural and physical barriers to development is crucial. For example, assessing the suitability of soil types for different developments, considering factors like agricultural productivity and load-bearing capacity, provides valuable information for future land-use decisions (Haines et al., 2005).

Cultural resources analysis

Cultural and historical aspects of a community shape a sense of place and guide recommendations for future land-use patterns in accordance with local culture and history. In-depth investigation of local sources of information is necessary to identify cultural heritages requiring special attention and preservation before any land-use change. A key consideration in this analysis is checking whether a resource is listed in the National Register of Historic Places or if a building or site may qualify for the registry (Haines et al., 2005).

Utility analysis

Utility analysis addresses utility system capacities in coordination with future land uses, providing a reliable understanding of existing and future infrastructure and major utility systems, such as sewage or treatment plants. Integrated land-use planning practices assess the amount, density, type, and location of future land uses to coordinate the utility system with the future land-use pattern, ensuring adequate service and protecting the infrastructure from damage or insufficient facilities (Haines et al., 2005).

Transportation system analysis

Transportation system analysis merges land-use planning with the transportation network and the mobility needs of residents and commercial and industrial activities. In addition to considering infrastructure and historical resources, it is important to understand the conditions, capacity, and location of roads adjacent and extended to new developments. Knowledge of transportation plans, such as highway system extensions and regional bike and pedestrian plans, is necessary when suggesting future land uses. Transportation facilities have a direct impact on accessibility, mobility rates, land prices, and density (Haines et al., 2005).

Growth factor analysis

Growth factor estimation helps planners predict factors like population, employment, auto ownership, and travel demand. This analysis assists planners in identifying natural and physical factors affecting how much and where a community may grow in the future. Understanding spatial growth patterns of the past helps identify growth directions, drainage basins, and environmental corridors for sensitive areas, farmlands, or future projects. All these considerations can be mapped as an independent layer in geographic information system software (Haines et al., 2005).

Zoning and build-out analysis

Development regulations, such as zoning and subdivision ordinances, and building codes are crucial for land-use analysis. They provide planners with information about permitted uses, entitlement processes, and development standards, such as setbacks and building height. This analysis may identify areas where future land-use designations conflict with the existing zoning map. Additionally, calculating activity areas at build-out informs future infrastructure needs to meet projected population (Haines et al., 2005).

Land-use demand projections

Demand projections involve identifying how much of each land-use category will be needed in the future. Different techniques and methods are applicable for various land-use classifications, considering their unique characteristics. For example, residential projection involves multiplying dwelling unit demand in the housing component of the municipal comprehensive plan by anticipated average residential densities over the next 20 years. Commercial and industrial land use indicators use current employee density (person per acre) to project total employment over the next 20 years and determine the needed area for commercial land uses (Haines et al., 2005).

Land-use suitability analysis

In this section, we will explore the common approach to land use suitability analysis for various land-use types using criteria classification scores and their respective weights. Urban and regional planners routinely engage in the essential task of evaluating land-use suitability for future developments. The outcomes of this analysis are pivotal for urban planning, management, and the assessment of development proposals. Mapping software, particularly ArcGIS, has been very  instrumental  in recent years in facilitating this process by evaluating diverse criteria, including environmental, social, and economic factors (Jafari & Zaredar, 2010, (Zone & Zone, 2008a).

The practice of Land-use Suitability Analysis (LSA) is gaining prominence in urban and regional planning. LSA aids in pinpointing the most fitting land use for a specific area, considering its environmental, social, and economic factors. This makes it a valuable tool for promoting sustainable land management. While land suitability assessment extends beyond geographical information systems, many urban planning professionals and scholars regard LSA as a significant contribution of ArcGIS.

As mentioned earlier, LSA data can encompass various parameters such as soil quality, slope, flood zones, water availability, road classification, accessibility, and activity density. Figure 5.1 illustrates the major steps involved in LSA and the expected results after completing the analysis. The final map, schematically presented on the right-hand side, represents better suitability  areas with higher contrasting colors.

To map the suitability of land for different land-use types, a crucial task involves linking various datasets to geospatial locations in ArcGIS. Once completed, the software generates a land-use suitability analysis across different scales and scenarios. Additionally, employing Land Suitability Analysis (LSA) with Geographic Information System (GIS) results in classifying urban and rural areas into zones with varying likelihoods or risks associated with different types of land use.

This mapped information is significant for land-use planning practices. The procedure, grounded in collected and analyzed data, is easy to apply and can be regularly updated (Puntsag et al., 2014).

Given that land-use suitability analysis demands a diverse set of data (criteria) for analysis, transportation data emerges as a crucial component. The integration of LSA with transportation models offers various benefits in the realm of land-use and transportation modeling. Many integrated plans in land use and transportation often begin with an analysis of existing conditions and assumptions about the distribution of future employment, residential areas, and population density.

However, by incorporating LSA into land-use transportation modeling, it becomes possible to better identify and map locations for various activities and land uses. In essence, LSA provides socio-economic and demographic projections for the future of the study area (Reibel et al., 2009). Figure 5.2 illustrates the general framework of an LSA for urban service deliveries. Following the preparation of the base map and delineation of the study area, different criteria and variables are mapped and overlaid. Subsequently, using the Analytic Hierarchy Process (AHP) model and expert opinions, each criterion is ranked, leading to the generation of a final score and map.

Steps  for land-use suitability analysis

The suitability analysis process involves overlaying maps containing diverse data types, such as physical, locational, and institutional information. The accumulated data results in a score indicating low, medium, or high suitability for a particular development. In Land-Use Suitability Analysis (LSA), the primary assumption is that the suitability score is a linear function of various factors. This method is popular due to its simplicity and appeal to decision-makers and analysts, especially when utilizing GIS (Malczewski, 2004).

According to this method, the suitability of a location ( i ) for land use ( j ) can be written as:

S is the ultimate score of a land for a certain land-use type,

F is the suitability of each factor based on their effects for a land I and land use type j , and

b is the coefficient or weight for suitability ratings.

The appropriate rating for different lands and land uses should be based on theoretical knowledge and frameworks that determine the most important affecting variables. As shown, factor weights are also very determining for suitability analysis results, and regression is a common tool for computing these weights. However, many scholars have suggested that when regression analysis is not available, Delphi technique or a multi-criteria evaluation technique , such as Analytical Hierarchy Process (AHP) (Wind & Saaty, 1980) can be implemented. The steps needed to complete the analysis are as follows:

1.      Step 1: Selecting a land-use category for analysis

2.      Step 2: Identifying the factors and their assigned values

3.      Step 3: Determine the score for various attributes for the factors

4.      Step 4: Weight the factors

5.      Step 5: Calculate a composite score from attribute value and weight for each factor

6.      Step 6: Rank the combined scores to establish suitability levels

7.      Identify the available land based on existing land use

8.      Constraints with comprehensive plans, zonings, or other land-use controls to further remove unavailable land

Step 1: Selecting a land-use category for analysis

Begin by selecting a specific land-use category for analysis within the Land Suitability Assessment (LSA). This involves examining the suitability of the land for different purposes, such as residential, commercial, or industrial use. In cases where multiple land-use types are proposed for a given area, establish a preference order.

Step 2: Identifying the factors and their assigned values

Identify the factors and their assigned values crucial for the analysis. Choosing these factors is a critical step, as they significantly influence the land’s suitability. Factors encompass diverse data, including the physical state of the land, cost-benefit analysis for the proposed land use, transportation, and utility considerations. It’s important to note that the number and nature of factors vary based on the type of land and its context. Consider local circumstances, available resources, natural hazards, key stakeholders, and residents’ needs to compile a relevant list of factors. For instance, emphasize the importance of accessibility in the analysis, considering factors such as satisfactory access to opportunities, transportation facilities, and utilities (as discussed in Chapter 4). For residential land use, proximity to supporting infrastructure and community facilities is advantageous. Consequently, areas closer to these facilities should be prioritized for development over more remote locations. Analyzing the existing infrastructure network is crucial to include the accessibility factor and assign appropriate values.

Step 3: Determine the score for various attributes for the factors

Proceed by determining the scores for various attributes related to the factors. Attributes may take different data structures, such as nominal, ordinal, interval, or ratio. For example, floodplain data can be nominal (inside or outside the 100-year floodplain ), while slope can be measured as a continuous ratio with values between 0 and 90 degrees. To ensure a robust suitability analysis, establish a clear linkage between the suitability score and attributes, ensuring that higher attribute values correspond to a higher level of suitability. Assigning scores may be a challenging task, requiring careful reordering and reclassifying (data cleaning). Refer to Table 5.1 for an example, which illustrates several factors with attributes converted to scores.

Step 4: Weigh the factors

In the fourth step of the Land Suitability Assessment (LSA), we focus on determining the significance of the identified factors by assigning weights to each of them. These assigned weights reflect the relative importance of each factor in comparison to others. The weights are typically expressed as percentages, ensuring that the cumulative sum of all factors equals 100%. It’s worth noting that different groups of experts may hold varying opinions regarding the importance and ranking of factors. Similar to step three of the analysis, the Delphi method can be employed in step four. In this method, a group of experts convenes to anonymously provide answers to a series of questions, including numerical value assignments to factors. Through several iterative feedback exchanges, a consensus on the weights can be reached (Grime & Wright, 2016). It’s important to mention that the Delphi method is not limited to step four; it can also be applied to step three. Table 5.2 serves as an example, illustrating weights assigned to five factors identified for assessing the land suitability of residential land use.

Step 5: Calculate a composite score from attribute value and weight for each factor

After identifying the appropriate factors and determining the scores and their weights, it is the time to calculate the composite score using the below formula:

S is the summation of the product of the individual weight,

Step 6 Rank the combined scores to establish suitability levels

After calculating the composite score for the study area, we should rank it based on certain thresholds in order to generate different classifications for land suitability. For instance, a score between 0 and 1 can represent least suitability and a score between 4 and 5 can indicate most suitability. A detailed example of a suitability ranking via scores is shown in table 5.3.

Step 7: Identify the available land based on existing land use

In the seventh step, the focus is on identifying areas suitable for the proposed land uses. A crucial consideration in this phase is the preference for areas with minimal human impacts and low intensity. This preference stems from the fact that it is generally uncommon to convert land with higher intensity to lower intensity. Consequently, new developments typically occur in undeveloped lands. For instance, farmlands and agricultural areas might be chosen for residential development. After calculating the composite score and comparing it with the characteristics of available lands, the goal is to pinpoint areas with the highest suitability for future developments. This step involves a strategic assessment to ensure that selected lands align with the intended land use and development objectives.

Step 8: Constraints with comprehensive plans, zonings, or other land-use controls to further remove unavailable land

In the final step, proposed developments are reviewed for alignment with municipal comprehensive plans and development regulations. This ensures conformity with environmental conservation areas and considers buffer zones or setbacks, limiting certain land uses and building placements. LSA analyzes ecological and environmental resources, excluding unsuitable areas and prioritizing lands for development within identified suitable zones.

A case study of LSA

The Land Suitability Assessment (LSA) discussed in this section was conducted by Luo Lingjun, He Zong, and Hu Yan in 2008. They utilized remote sensing and GIS technologies, applying the LSA to urban-rural land planning in China. The analysis focused on the Lianping area in China and employed factors derived from land-use interpretation of TM (Thematic Mapper) images. The key factors considered in this analysis included natural limiting factors, economic construction, ecologically sensitive factors, and ecological protection factors. Each of these overarching categories consisted of several sub-factors, which will be elaborated on in the subsequent pages.

The initial step of this study involved identifying and classifying existing land-use types in the Lianping area. This information is crucial as the current land use can act as a significant barrier or motivation for future development. Additionally, the distribution of land uses in the area plays a pivotal role in influencing planned land uses. The classification of lands in this study area encompassed various types, including arable land, woodland, grassland, construction sites, development land, water bodies, and unused lands (Zone & Zone, 2008b). This comprehensive classification laid the foundation for the subsequent steps in the land-use suitability assessment.

Table 5.4 shows the classification of the area’s terrain, one of the most important factors in LSA. The average elevation is 450 meters, and the assignment of scores is based on this value.

The initial step involved identifying and classifying existing land-use types in the Lianping area, such as arable land, woodland, grassland, construction sites, development land, water bodies, and unused lands (Zone & Zone, 2008b). Understanding current land use is crucial, as it influences both barriers and motivations for future development.

Table 5.4 demonstrates the classification of terrain based on elevation, a significant factor in LSA. The scores are assigned according to surface elevation values, with higher scores indicating stronger limitations.

Similar to terrain factors, landscape, proximity to towns, accessibility, proximity to transportation facilities, and ecological sensitivity were selected and assigned scores based on various attributes. The choice of factors depends on the analysis objectives, land development purposes, previous practices, and major characteristics of the study area.

Following factor identification and classification, the next crucial step involved determining the relative weight for each criterion. In this study, the Delphi method, incorporating experts’ consensus on the importance of the factors was employed to calculate weights. The results are presented in Table 5.5.

With the factor weights determined, the study employed ArcGIS for spatial data overlay, resulting in visual maps for each factor and an aggregate final score (suitability result), as depicted in Figure 5.3.

Land-use classification

Land-use classification serves as a fundamental data type in Land-Use Suitability Analysis (LSA). It’s aim is to differentiate between various uses and establish appropriate development standards. The roots of land classification trace back to the 1950 report titled “Urban Land Use” by the American Society of Planning Officials. This report documented the profession’s efforts to standardize the mapping and designation of different land uses for analytical purposes. The result was the creation of standardized broad categories of land use, including residential, multifamily, commercial, industrial, railroad, parks, streets, semi-private areas, and more. Since 1950, two major approaches have evolved for classifying land uses: The Standard Land Use Coding Manual (SLUCM) and the Land-Based Classification Standards (LBCS). These coding systems offer greater detail, encompassing additional dimensions of land use, such as typical land use or the type of activity on a parcel, ownership data, density, and structure. Prior to 1950, the firm of Harland Bartholomew & Wood developed a land-use classification applied to the many comprehensive plans that the firm produced for cities across the nation. Land uses were initially categorized into a two-tiered system, where the first level identified the land use category, distinguishing between vacant or developed land, whether private or public. The second level provided details about the type of structures. This approach is straightforward and was later expanded to include ownership data.

The Standard Land Use Coding Manual (SLUCM) originated in 1965 from a collaboration between the Bureau of Public Roads and the Urban Renewal Administration. This classification system involved four levels of coding, utilizing a 4-digit code to characterize each parcel. Published jointly by the Federal Highway Administration and the Department of Housing, the SLUCM established a comprehensive list of land-use categories with numeric codes based on the Standard Industrial Classification (SIC) system in 1965. It quickly became the nationwide standard for urban land-use coding. Although a reprint was issued in 1972, its usage waned in the late 1970s due to a shift in land-use planning focus towards short-term, small-scale projects, with a reduced emphasis on long-term planning (American Planning Association, 1994). Table 5.7 shows an example of land use classification for residential usage in the City of Dallas, TX. This table is a showing a snapshot of the original table (for the original table follow: City of Dallas Residential Landuse Classification ).

The Land-Based Classification Standards (LBCS), developed by the research department of the American Planning Association in 1994, is likely the most comprehensive land classification system. Serving as an extension of the 1965 SLUCM, this approach features a multi-aspect and multi-scale data structure, encompassing five attributes of land use: activities, functions, building types, site development character, and ownership. However, a 2012 review by the American Planning Association’s research team noted limited adoption of LBCS at the local level. Despite its advantages in specificity and flexibility over single-purpose classification systems, LBCS faces limited deployment. This lack of adoption may stem from a simple lack of awareness among planners (APA, 2012, p. 10). The activity dimension in LBCS pertains to the direct human use of land (American Planning Association, 2009). However, the 2012 review by the American Planning Association’s research team highlights that LBCS adoption at the local level remains limited. Considering its code structure, LBCS could prove beneficial for LSA and integrated land-use transportation modeling.

Table 5.8 displays categories for activity-based classification, illustrating that certain categories can have second-level classifications as well.

Function of the land is the second dimension in this classification system that communicates the economic function or the type of the establishment. In this dimension, each category can be further classified according to different properties of each function. For instance, residence or accommodation functions can include homes, apartments, as well as hotels. Table 5.8 shows some of these functions classifications.

The structure dimension focuses on the establishment’s physical structure on the land, emphasizing the building developed for the land rather than the activity or function. Similar to previous dimensions, structure can be divided into four levels. For instance, in the case of residential buildings, the second level identifies whether the building is for a single-family unit, multi-family unit, or other specialized residential structures. In the next level, it identifies whether the building is detached units, attached units, or manufactured housing. The fourth level includes other properties such as duplexes, zero lot line structures, row houses, etc. (American Planning Association, 2009).

It is worth noting here that LBSC and SLUCM are two of the widely adopted classification methods used within the context urban planning in the US, although certain cities and regions may develop their own customized version of classification system that is tailored for their specific needs and contextual features. While SLUCM is more focused on land use activities, LBCS has classifications for land cover as well. Additionally, both methods use a hierarchical structure with multiple levels of subcategories, however LBCS is more comprehensive in terms of range of subcategories. Furthermore, it is believed that LBCS can be better customized for specific needs compared to SLUCM and may better integrate with GIS for mapping and analysis purposes. That said, SLUCM is more widely used local government and planning agencies for land use planning, zoning, and development standards, while LBCS is more common for federal agencies and research institutions.

Site development is another dimension in this system that represents data about the physical features of the land. Its three main classes are site in a natural state, developing land, and developed lands. However, for some lands, this dimension might not be applicable. Table 5.9 illustrates this dimension in the LBCS classification system.

The ownership dimension is the last dimension in the LBCS system, through which the ownership data is classified. The three main general categories in this dimension are: privately owned, public and non-profit sectors, or jointly owned lands. In the following table, various kinds of ownership status are observable. The 2000 category that is labeled as easement restraint refers to a landowner who does not have the sole right of use of the property. Like the previously discussed dimensions discussed here, ownership can also be further categorized into lower levels. For instance, for the lands classified as public restrictions, the next level could be the administrative level of the public owner like state, federal, or even for local government, such as city, village, township, etc.

Note. From “LBCS Ownership Dimension with Descriptions” by American Planning Associaton. 2009 (https://www.planning.org/lbcs/standards/ownership/).

5.6 Land databases and mapping

For many years, land data storage was manual, involving the creation of parcel map books. These books, predating the era of computers and digital data storage, assigned a unique Property Identification Number (PIN) to each parcel. Most data, including ownership and land-use type, was recorded using this PIN. Whether in paper-based archives or computerized systems, a common structure for recording land data is a map containing all parcels and associated data with a PIN (Wang & Hofe, 2020). In computerized land-use databases, data tables play a central role. Each row represents a parcel, and each column signifies a variable. An advantageous feature in computerized versions is the ability to join different tables and data using a key field. A key field is a column containing unique values for parcels. There are four types of relationships: one-to-one , many-to-one , one-to-many , and many-to-many . In a one-to-one relationship, one key value in one table matches at most one matching key value in the second table. The connection is typically established using a key variable, often a Feature Identifier Field (FID), appearing only once in each table (Bansal & Pal, 2005). In the many-to-one relationship, the key values in the first table may be duplicated, while the second table maintains unique values. Consequently, records in the first table can be linked to a single key in the second table. Figure 5.4 illustrates a two-step merging of three tables using two key fields related to parcel (tax) information.

One-to-many is a relationship in which the key field in the first table contains unique values and the key field in the second table has duplicated values. In other words, in this joining of tables, we merge one record in the first table to multiple records in the second table.

The last type is called many-to-many, where both key fields in the two tables have duplicated values. In this mode, one record in table one can be linked to multiple records in table two and vice versa. For example, we may have various densities within a zip code area, and one particular density may appear in many zip codes. An intermediate table may be needed to connect two tables for this kind of relationship. Figure 5.5 schematically shows how to join different tables using one-to-one, many-to-one, and one-to-many relationships.

In this chapter we reviewed LSA which stands as a powerful and pivotal tool in urban land management. LSA is a multi-step process and this chapter focused on one method for performing LSA. Several other techniques such as index overlay, multi-criteria evaluation, fuzzy logic, machine learning and image classification exists in practice than can utilized depending on local requirements or availability accurate data. As we demonstrated in the case study example, research is still going on to advance techniques of LSA and generate insights for urban planning field. We also reviewed some of the widely-used land use classification systems in the US and highlighted the importance of adoption of such systems for interoperability and reliability of land use data in GIS for planning purposes. With such a rapid rate of urbanization worldwide, and emerging challenges for sustainable development, the usefulness of these evidence-based approaches for informing land use decisions cannot be overstated.

• Regional context analysis is a technique for identifying and assessing the surroundings of a community that includes “statewide natural features, economic development efforts, transportation locations and decisions, and the plans and actions of nearby communities and other agencies” (Haines et al., 2005, p.27).
• Community opportunities analysis kind of analysis that helps us to address and decide how opportunities affect future land use.
• Cultural resources analysis type of analysis mainly revolves around the cultural and historical aspects of a community and helps planners to suggest future land-use patterns in accordance to local culture and history
• Utility analysis is an analysis that tries to address the utility system capabilities and their coordination with future land uses
• Transportation system analysis is usually the same as land use and transportation modeling since it is seeking to integrate land-use planning with the transportation network and residents’ mobility needs
• Growth factor analysis is a tool at hand for planners for predicting different factors like population, employment, auto ownership, travel demand, etc
• Land-use suitability is geospatial tool that is used for identifying the most suitable for a particular land use.
• Linear function is a type of relationship between two quantities that forms a straight line with constant slope.

Delphi technique is structured communication with experts to use their input for decision -making.

Multi-criteria evaluation technique is a GIS-based tool to identify the most suitable land for a purpose by a multiple criteria.

Analytical Hierarchy Process is technique for structing the decision making using by quantifying the alternatives and criteria through pairwise comparison to find the best solutions.

100-year floodplain is a referred to an area for which the probability of having flood in any given year is 1%.

Land-use classification is a principal type of data that we need for land-suitability analysis, and we typically base the analysis on the information derived from land-use classification.

Property identification number a unique number assigned to each parcel by parcel map book which is connected various data like ownership.

One-to-one is a type of relationship between an object that can relate only to one destination or description.

Many-to-one is a type of relationship between multiple objects in the first table and one single record in destination table.

One-to-many is a type of relationship between one object in the first table or layer to many objects in the destination table.

Many-to-many is when one object in first table can be related to multiple objects in the destination table and vice versa.

Feature identifier field (FID) a value that is created, assigned and managed by GIS functions to identify a feature or object.

Key Takeaways

In this chapter, we covered:

• Land-use planning and analysis are important tasks in urban planning and development, and various types of data are needed and should be collected for this analysis.
• LSA generally contains eight subsequent steps, by which the most suitable land for a particular land use can be discovered.
• Numerous data records and land-use classifications exist, all of which store certain information about a piece of land such as activity, structure, ownership, etc.
• Four types (techniques) for joining spatial information stored in tables can be used for creating GIS datasets.

Prep/quiz/assessments

• What are the major considerations before starting any land-use development analysis and allocation of lands to activities? Explain any two of them.
• What is the importance of land-use suitability analysis in urban planning and development, and what are general ways to quantify land characteristics?
• What are the steps for land-use suitability analysis and assumptions for creating a suitability score?
• What is the difference between one-to-one, one-to-many, and many-to-one techniques for joining GIS tables?

American Planning Association. (1994). Toward a standardized land-use coding standard . Bureau of Public Roads and the Urban Renewal Administration. https://www.planning.org/lbcs/background/scopingpaper/

American Planning Association. (2009). Land-based classification standards . Http://Myapa. Planning. Org/Lbcs/.

Anderson, J. R. (1976). A land use and land cover classification system for use with remote sensor data (Vol. 964). US Government Printing Office.

Bansal, V. K., & Pal, M. (2005). GIS in construction project information system . In Proceedings of Map India, 8th Annual International Conference and Exhibition in the Field of GIS, GPS, Arial Photography, and Remote Sensing. India https://www.academia.edu/531265/GIS_in_Construction_Project_Information_System

Bartholomew, H., & Wood, J. (1955). Land use in american . Harvard University Press. https://www.amazon.com/Land-American-Cities-Harland-Bartholomew/dp/0674509005

Burley, T. M. (1961). Land use or land utilization? The Professional Geographer , 13 (6), 18–20. https://doi.org/10.1111/j.0033-0124.1961.136_18.x

GISGeography. (2022, March 15). Relate vs Join: Cardinality for Attribute Tables in ArcGIS. GIS Geography . https://gisgeography.com/relate-vs-join-attribute-tables-arcgis/

Grime, M. M., & Wright, G. (2016). Delphi method. In P. Brandimarte, B. Everitt, G. Molenberghs, W. Piegorsch, & F. Ruggeri (Eds.),  Wiley StatsRef : Statistics Reference Online  (pp. 1-6). John Wiley & Sons Inc. https://doi.org/10.1002/9781118445112.stat07879

Haines, A., Walbrun, C., Kemp, S., Roffers, M., Gurney, L., Erickson, M., & Markham, L. (2005). Land use resource guide . Center for Land Use Education, University of Wisconsin-Stevens Point/Extension.

Jafari, S., & Zaredar, N. (2010). Land suitability analysis using multi attribute decision making approach. International Journal of Environmental Science and Development , 441–445.  https://doi.org/10.7763/ijesd.2010.v1.85

Joerin, F., Thériault, M., & Musy, A. (2001). Using GIS and outranking multicriteria analysis for land-use suitability assessment.  International Journal of Geographical information science ,  15 (2), 153-174. https://doi.org/10.1080/13658810051030487

Luan, C., Liu, R., & Peng, S. (2021). Land-use suitability assessment for urban development using a GIS-based soft computing approach: A case study of Ili Valley, China. Ecological Indicators , 123 , 107333. https://doi.org/10.1016/j.ecolind.2020.107333

Loi, N. K. (2010). Integration of GIS and AHP Techniques for Analyzing Land Use Suitability in Di Linh District, Upstream Dong Nai Watershed, Vietnam. Southeast Asian Regional Center for Graduate Study and Research in Agriculture (SEARCA) (No. 2010-2)

Lingjun, L., Zong, H., & Yan, H. (2008). Study on land use suitability assessment of urban-rural planning based on remote sensing—A case study of Liangping in Chongqing. Remote Sensing Technology and Application , 2008, 23(6): 662-666.https://www.isprs.org/proceedings/xxxvii/congress/8_pdf/1_wg-viii-1/22.pdf

Malczewski, J. (2004). GIS-based land-use suitability analysis: a critical overview.  Progress in Planning ,  62 (1), 3–65. https://doi.org/10.1016/j.progress.2003.09.002

Puntsag, G., Kristjánsdóttir, S., & Ingólfsdóttir, B. (2014). Land suitability analysis for urban and agricultural land using GIS: Case study in Hvita to Hvita, Iceland. United Nations University Land Restoration Training Programme . https://www.grocentre.is/static/gro/publication/434/document/puntsag2014.pdf

Wang, X., & Hofe, R. vom. (2020). Selected methods of planning analysis . Springer Singapore, Imprint Springer.

Wind, Y., & Saaty, T. L. (1980). Marketing applications of the analytic hierarchy process. Management Science , 26 (7), 641–658.   https://doi.org/10.1287/mnsc.26.7.641

Transportation Land-Use Modeling & Policy Copyright © by Qisheng Pan and Soheil Sharifi is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 18 June 2021

Scenario simulation of land use and land cover change in mining area

• Xiaoyan Chang 1 ,
• Feng Zhang 1 ,
• Kanglin Cong 1 &
• Xiaojun Liu 1  

Scientific Reports volume  11 , Article number:  12910 ( 2021 ) Cite this article

4567 Accesses

24 Citations

1 Altmetric

Metrics details

• Environmental sciences

In this study, we selected 11 townships with severe ground subsidence located in Weishan County as the study area. Based on the interpretation data of Landsat images, the Binary logistic regression model was used to explore the relationship between land use and land cover (LULC) change and the related 7 driving factors at a resolution of 60 m. Using the CLUE-S model, combined with Markov model, the simulation of LULC under three scenarios—namely, natural development scenario, ecological protection scenario and farmland protection scenario—were explored. Firstly, using LULC map in 2005 as input data, we predicted the land use spatial distribution pattern in 2016. By comparing the actual LULC map in 2016 with the simulated map in 2016, the prediction accuracy was evaluated based on the Kappa index. Then, after validation, the spatial distribution pattern of LULC in 2025 under the three scenarios was simulated. The results showed the following: (1) The driving factors had satisfactory explanatory power for LULC changes. The Kappa index was 0.82, which indicated good simulation accuracy of the CLUE-S model. (2) Under the three scenarios, the area of other agricultural land and water body showed an increasing trend; while the area of farmland, urban and rural construction land, subsided land with water accumulation, and tidal wetland showed a decreasing trend, and the area of urban and rural construction land and tidal wetland decreased the fastest. (3) Under the ecological protection scenario, the farmland decreased faster than the other two scenarios, and most of the farmland was converted to ecological land such as garden land and water body. Under the farmland protection scenario, the area of tidal wetland decreased the fastest, followed by urban and rural construction land. We anticipate that our study results will provide useful information for decision-makers and planners to take appropriate land management measures in the mining area.

Similar content being viewed by others

1 km land use/land cover change of China under comprehensive socioeconomic and climate scenarios for 2020–2100

Prediction of land use for the next 30 years using the PLUS model's multi-scenario simulation in Guizhou Province, China

Mapping the spatial heterogeneity of global land use and land cover from 2020 to 2100 at a 1 km resolution

Introduction.

With global environmental changes and deepening research of sustainable development, the study of Land Use and Land Cover (LULC) Change has attracted more and more attention of the researchers worldwide. The focus of research has also gradually shifted from large scale at territory or regional scale to ecologically fragile areas such as wetland 1 , 2 , river basin 3 , 4 , 5 , 6 and mining area 7 , 8 .

The landscape of mining area is featured mainly by mining and other human production activities. While extensive coal mining boosts regional economy, it also brings significant environmental changes such as severe ground subsidence, land resource destruction, water resource pollution, etc., and often exacerbates the ecosystem fragility in mining area. Land rehabilitation, implying the reclamation of post-mining land subsidence, has complicated intertwined impacts, directly or indirectly, on the structure, composition and function of ecosystem in mining area. The driving force analysis can reveal the evolution law and driving mechanism of regional LULC change 5 , 9 , 10 . On this basis, scenario simulation predicts the future trend of LULC change 11 , 12 , 13 . Scenario simulation results not only provide theoretical foundation for the local government to formulate scientific, plausible and sustainable land use development strategies, but also have great significance for the protection of land resources and the improvement of regional ecological environment.

The research results of domestic and foreign scholars on scenario simulation models of LULC showed that single model cannot satisfy both quantitative simulation and spatial pattern analysis simultaneously. Therefore, scenario simulation is gradually changing from using single model to multiple integrated models 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 . Previous studies have suggested that logistic regression model can better reveal the main driving forces and interaction mechanisms of LULC change 11 , 26 , 27 , 28 , 29 . Binary logistic regression model (BLRM) is good for binary dependent variables, while multinomial logistic regression model is more suitable for multivariate dependent variables. Logistic regression model is often used for driving factors analysis of LULC change in ecologically fragile areas such as reservoir area 11 , 26 , mountainous area 29 , etc. And it is also mainly used for driving factors analysis of urban land use change 27 , 28 . Based on the results of logistic regression analysis, scenario simulation is often carried out. Using the Conversion of Land Use and its Effects at Small regional extent (CLUE-S) model, we can take into account many kinds of factors, preset multiple scenarios and visualize spatial patterns of LULC under different scenarios 30 , 31 , 32 , 33 , 34 , 35 , 36 .

In this study, mining area with severe ground subsidence problems was selected as the study area. Based on the 30 m interpretation data of Landsat images, firstly, 60 m was determined as the appropriate spatial resolution for driving forces analysis. At the suitable spatial resolution, BLRM was used to explore the relationship and driving mechanism between LULC types and driving factors. The results showed that the driving factors had satisfactory explanatory power for LULC changes. On this basis, using the CLUE-S model, combined with Markov model, the spatial distribution pattern of LULC in 2025 under three scenarios—namely, natural development scenario, ecological protection scenario and farmland protection scenario—was simulated and predicted. The results can guide the local government to formulate scientific and reasonable land use sustainable development strategies in land reclamation and optimal allocation of land resources, which has great significance for the rational development, utilization and protection of land resources.

The novelty of our research and scientific contributions are summarized as follows: (1) Different from the current scenario simulation research, when analyzing the relationship and driving mechanism between LULC types and driving factors, we mainly used BLRM and the entropy theory to determine the appropriate spatial resolution of 60 m. However, most of the related researches only determined the research scale subjectively, which was lack of scientificity and basis. (2) Before the scenario simulation of LULC in the future, firstly, using LULC map in 2005 as input data, we predicted the spatial distribution pattern of LULC in 2016. By comparing the actual LULC map in 2016 with the simulated map in 2016, the prediction accuracy was evaluated. On the basis of the prediction results meeting the accuracy requirements, natural development scenario, ecological protection scenario and farmland protection scenario were designed, and we simulated and predicted the futural LULC spatial distribution pattern of the mining area, which increased the accuracy and credibility of the prediction results. Our study process also provides a reference for the related research of scenario simulation.

Geographical location and mining area distribution in the research area. Maps were generated using ArcGIS 10.1 for Desktop ( http://www.esri.com/software/arcgis/arcgis-for-desktop ).

Weishan county( \(34^\circ 27\) ′N to \(35^\circ 20\) ′N, \(116^\circ 34\) ′E to \(117^\circ 24\) ′E), is located in the southern part of Jining City, Shandong Province. The study area is 120 km long from north to south, 8–30 km wide from west to east. Nansi Lake, the largest freshwater lake in northern China, is located within the study area. Weishan county comprises 3 sub-districts, 10 towns, 2 townships and 1 economic development zone (2014 administrative division), with a total area of 1779.8 km 2 . We selected 11 townships with a total area of 1176.86 km 2 , because this study area has more mines, more severe land subsidence, and is spatially coherent. The geographical location of the study area and the distribution of mining area are shown in Fig. 1 .

Data and methods

Data source and preprocessing.

Considering factors such as amount of cloud and time intervals of image, four remote sensing images with a spatial resolution of 30 m, including Landsat 5 Thematic Mapper (TM) images for 08-21-2000, 09-04-2005 and 09-18-2010, and Landsat 8 Operational Land Imager (OLI) for 09-02-2016,were obtained from the Geospatial Data Cloud Platform ( http://www.gscloud.cn ). LULC information was extracted from these remote sensing images. In addition, the digital elevation model (DEM) with a spatial resolution of 30 m was obtained from the website. Elevation and slope information were derived from DEM data and used as terrain driving factors for scenario simulation. Other supporting data, such as Weishan County land use data, mine distribution data, general land use planing (2006–2020) and mineral resources planning (2008–2015), Jining City coal mining subsidence land rearrangement planning (2016–2030), were obtained from Weishan Natural Resources and Planning Bureau. These data were used for better data analysis.

Considering severe ground subsidence and seeper in the study area, and referring to national standards: Current Land Use Classification (GB/T 21010-2017), remote sensing images were interpreted into six LULC types: farmland, other agricultural land, urban and rural construction land, subsided seeper area, water area, and tidal wetland.

In the process of image interpretation, firstly, the remote sensing image was divided into two regions: one region were the lake and the surrounding tidal wetland, and the other region included farmland, other agricultural land, urban and rural construction land, subsided seeper area, etc.

In region 1, decision tree classification, combined with the Modified Normalized Difference Water Index (MNDWI), was used to extract lakes. Then we masked them in region 1. The Normalized Difference Vegetation Index (NDVI) was calculated for the remaining image of region 1. Tidal wetland was mainly distributed along rivers and lakes, and NDVI value was higher than that of farmland and other vegetation. By analyzing its geographical distribution and NDVI value, and referring to Weishan County land use data, the appropriate threshold was selected to extract tidal wetland.

The spectral signature of rivers, ditches and aquaculture ponds in other agricultural land in region 2 could be easily distinguished from other surface features. They could be extracted step by step by manual visual interpretation and empirical knowledge, referring to Weishan County land use data and water system data. Then we masked them separately in region 2. After extracting rivers, ditches, aquaculture ponds with high water content, the remaining LULC type with high water content in region 2 was subsided seeper area. According to the relationship of spectral signature of different LULC types, it was concluded that among the remaining LULC types in region 2, only TM3 band value of subsided seeper area was higher than TM5 band value. Using this characteristic, subsided seeper area could be distinguished from other LULC types. After extracting subsided seeper area, the remaining LULC types in region 2 were farmland and urban and rural construction land. The spectral characteristics of them were very different. Therefore, they could be distinguished using support vector machine (SVM) classification method, and their respective binary images were generated using decision tree method.

The extracted six LULC types were shown in single layer and binary form respectively. Six LULC types were coded and synthesized into one image. We obtained 2000, 2005, 2010, 2016 LULC type maps (Fig. 2 ). Finally classification post-processing and accuracy evaluation were operated.

The LULC types maps of 2000, 2005, 2010 and 2016. Maps were generated using ArcGIS 10.1 for Desktop ( http://www.esri.com/software/arcgis/arcgis-for-desktop ).

The accuracy of the interpretation results was verified by confusion matrix and kappa coefficient. The kappa coefficients of the four interpretation maps were 0.84, 0.85, 0.82 and 0.86, respectively (Table 1 ). The accuracy could meet the needs of further research.

By reading previous research results 37 , 38 , 39 , 40 , 41 , based on the entropy theory, in the same study area, high spatial resolution data contains more entropy than low spatial resolution data, and reflecting more detailed information, but it will increase the uncertainty of prediction results and reduce the prediction accuracy. Although the prediction accuracy of low spatial resolution data increases, it will lose lots of detailed information. In order to ensure the accuracy of the simulation, considering the area of the study area and data requirement of the CLUE-S model, the interpreted LULC maps with a resolution of 30 m exceed the upper limit of the CLUE-S model data requirement, so the LULC maps were resampled to multiple scales including 60 m, 90 m, 120 m, and 150 m to facilitate logistic regression analysis of LULC types and driving factors.

Selection and processing of driving factors

To interpret the relationship between the LULC and its driving factors in the mining area, we not only need to identify the driving factors that have greater explanatory power for LULC change, but also need to quantitatively describe the relationship between driving factors and LULC types.

Considering the accessibility, usability of the data and the actual conditions in the study area, seven driving factors were selected based on the land use map of Weishan County in 2005 and the DEM data 5 , 10 , 11 , 13 , 26 , 28 , 29 , 30 . The driving factors included: (1) terrain factors, including elevation and slope factors; (2) five accessibility factors, including the nearest distance between each grid pixel and the main roads, the major rivers, the residential area, the major mines, and the ditches. The 30 m grid data of each driving factor were resampled to 60 m, 90 m, 120 m and 150 m respectively.

In this study, BLRM was used to explore the relationship between LULC change and the related 7 driving factors. BLRM is sensitive to multicollinearity. In order to eliminate the influence of collinearity on the regression results, the multicollinearity between independent variables was diagnosed before the regression model was established.

The receiver operating characteristic (ROC) curve was used to evaluate the accuracy of regression analysis results at different scales. The results showed that using 60 m resolution provided more accurate regression analysis results and suffered less loss of LULC and driving factor information during resampling. Therefore, we used 60 m × 60 m grid cell data to driving forces analysis.

Raster maps of each driving factor at a resolution scale of 60 m are shown in Fig. 3 .

Raster maps of driving factors at a resolution scale of 60 m. Maps were generated using ArcGIS 10.1 for Desktop ( http://www.esri.com/software/arcgis/arcgis-for-desktop ).

Logistic regression analysis of LULC types and driving factors

BLRM is often used for regression analysis of explanatory binary variables. The presence and absence of a certain type of LULC in a specific area is set as 1 and 0, respectively, which is characteristic for binary variable. Therefore, we used BLRM to calculate the probability ( P ) of various LULC types in a specific spatial location, and its mathematical expression is:

where \(\frac{P}{1-P}\) is the ’odds ratio’ of an event, abbreviated as \( \Omega \) , which represents the odds that an outcome will occur given a particular condition compared to the odds of the outcome occurring in the absence of that condition; \(\beta _0\) is a constant; \(\beta _1\) is the correlation coefficient of an explaining variable and an explained variable. Making mathematical transformation of the above expression, we get: \(\Omega = (\frac{P}{1-P}) = e^{\beta _0 + \beta _1 X}\) .

Regression analysis using BLRM, we divided the study area into many grid cells. Taking each LULC type as the explained variable, and the driving factor causing LULC change as the explanatory variable, we calculated the odds ratio of each LULC type in a specific spatial location, and analyzed the relationship between each LULC type and the driving factors. The calculating equation is:

Making mathematical transformation of the above equation, we get:

where: \(P_i\) is the probability of a certain LULC type i in a grid cell, \(X_{1,i}\sim X_{n,i}\) are the driving factors of LULC type i , \(\beta _0\) is the constant, \(\beta _1\sim \beta _n\) are the correlation coefficients of each driving factor and LULC type i .

The receiver operating characteristic (ROC) was used to evaluate the accuracy of regression analysis results. The accuracy can be measured by calculating the area under the ROC curve. The area value is between 0.5 and 1. The closer the value is to 1, the higher the accuracy is. In general, the area under the ROC curve is greater than 0.7, which indicates that the selected factor has good explanatory power 27 , 42 .

CLUE-S simulation and accuracy validation

Before using the CLUE-S model for futural LULC scenario simulation in mining area, the prediction accuracy needs to be verified. Based on the data of LULC in 2005, the spatial distribution pattern of LULC in 2016 was predicted firstly.

The modeling accuracy was evaluated based on the Kappa index by comparing the actual LULC map in 2016 with the simulated in 2016 27 , 43 , 44 . Equation ( 4 ) gives one of the most popular Kappa index equations: i.e.,

where \(P_o\) is the observed proportion correct, \(P_c\) is the expected proportion correct due to chance, \(P_c\) =1/ n , n is the number of LULC types, and \(P_p\) is the proportion correct when classification is perfect.

In order to further verify the accuracy of the model simulation, we also calculated kappa for quantity (Kquantity).

Scenario setting of futural LULC simulation

Due to the continuous population growth and mineral exploitation in the study area, the land resources, especially farmland resources, have become increasingly scarce and the environment has been deteriorating. Based on the simulation and validated results during 2005-2016, we defined three scenarios—namely natural development scenario, ecological protection scenario, and farmland protection scenario—to predict LULC spatial patterns for 2025.

Natural development scenario

In this scenario, the land use demand of the study area was basically not restricted by policies in near future. We assumed that the change rate of each LULC type in near future was consistent with the change trend from 2005 to 2016. So it is defined as natural development scenario. Using Markov model to obtain the area transition probability matrix of each year from 2017 to 2025, and taking the proportion of each LULC type area in the total study area in 2005 as the initial state matrix, the area of each LULC type in 2025 under the natural development scenario was predicted.

Based on the characteristics and trend of the LULC change from 2005 to 2016, after appropriately adjusting the transition probability matrix of different LULC types, we predicted the demands of each LULC type in 2025 under ecological protection scenario and farmland protection scenario using Markov model 45 , 46 .

Ecological protection scenario

This scenario emphasizes protecting the ecological environment, restricting the conversion of the LULC types that have more regulatory effects on the ecosystem, such as tidal wetland and water area, to other land use types. Garden land, woodland, grassland, and aquaculture land, belong to other agricultural land, which have regulatory effects on the local ecosystem, so their conversion to other LULC types should be restricted as well.

Farmland protection scenario

According to the guidelines of “the general land use planning in Weishan County (2006-2020)”, we should maximize the potential use of current construction land, implement intensive and economical utilization of construction land, and use less or not use farmland to economical construction. So in order to ensure the dynamic balance of total farmland amount and the regional food supply security, in the farmland protection scenario, the conversion from farmland to other land use types should be restricted. The projected land use demands for 2025 under the three different scenarios are shown in Table 2 .

Multicollinearity diagnostic result of driving factors

In this study, tolerance and variance inflation factor were used to diagnose the multicollinearity of driving factors. The results are shown in Table 3 .

The minimum tolerance of the seven driving factors was 0.207, which was greater than the critical value of 0.1. The maximum variance inflation factor was 4.833, less than the critical value of 5. It showed that there was no multicollinearity relationship among the seven driving factors.

Regression analysis result of LULC types and driving factors

The relationship between each LULC type and the driving factors was obtained using BLRM 11 , 29 . Firstly, the zero-mean normalization method was used to standardize the driving factors data. The β coefficients (listed in Table 4 ), derived from the logistic regression equation, were used as input parameters for the CLUE-S model. Table 4 shows that the distance to residential area was the main driving factor for the change of urban and rural construction land, and there was obvious negative correlation between them, which suggested the probability of construction land occurrence was relatively less in areas far away from the residential area. There was a significant negative correlation between subsided seeper area and the distance from mines, main rivers, and roads, suggesting that the probability of subsidence water area occurrence increased around mines, rivers and main roads. The distance to river was a negative explanatory variable for other agricultural land, suggesting that areas far away from major rivers would show smaller probability of other agricultural land. In particular, aquaculture land is one of the land use types of other agricultural land, aquaculture land area would drop significantly as the distance to river increased. The distances to major ditches and roads were significant negative explanatory variables for water area and tidal wetland.

ROC curves for regression analysis of LULC type and driver factors.

The area values under the ROC curve were as shown in Fig. 4 : farmland 0.793, other agricultural land 0.639, urban and rural construction land 0.940, subsidence seeper area 0.815, water area 0.903, tidal wetland 0.795. Except for other agricultural land, the values of ROC of other LULC types were above 0.70, which suggested the selected driving factors could better simulate the spatial pattern of land use. The probability distribution of the simulated land use types was consistent with that of the actual land use types. The ROC value of other agricultural land was slightly lower, the reason may be that other agricultural land includes garden land, woodland and grassland, so the simulation effect was not good.

Accuracy validation of scenario simulation results in 2016

The spatial overlay analysis of the simulated LULC map and the real map in 2016 was carried out, and the calculated \(P_o\) value was 0.857. In this study, the land use types were 6, so \(P_c\) =1/6. \(P_p\) is the correct simulation proportion under the ideal classification, \(P_p\) =1. So the Kappa index was calculated as 0.829, larger than 0.75. Kquantity was 0.978. Those indicated satisfactory accuracy and suggested that the CLUE-S model could be used to simulate the LULC change in the future under different scenarios.

Prediction of futural LULC spatial distribution pattern under different scenarios

The demands of each LULC type under three different scenarios were input into the CLUE-S model. Meanwhile, according to the LULC change in the study area from 2000 to 2016, the conversion elasticity values of each LULC type in the future scenario simulation were preliminarily determined. During the simulation, by comparing the simulation results with the set scenarios, the conversion elasticity values were repeatedly adjusted. Finally, the conversion elasticity coefficient values of each LULC type under three different scenarios were determined as shown in Table 5 .

The BLRM was established and validated to explore the relationship between driving factors and LULC types. Using the selected 7 driving factors and LULC data in 2016 as input data for simulation, the spatial distribution of each LULC type in 2025 under three different scenarios were predicted after fine-tuning configuration of model parameters. The prediction results are shown in Table 6 and Fig. 5 .

LULC simulation maps in 2025 under different scenarios. Maps were generated using ArcGIS 10.1 for Desktop ( http://www.esri.com/software/arcgis/arcgis-for-desktop ).

LULC characteristics in the future

As shown in Table 6 and Fig. 5 , other agricultural land and water area increased under the three scenarios. It showed that ecological land, such as other agricultural land and water area, which play an important role in regulating the regional ecological environment, has attracted more and more attention from 2017 to 2025. Farmland, urban and rural construction land, subsided seeper area and tidal wetland showed a shrinking trend. And the single dynamic degree of tidal wetland and urban and rural construction land were the largest, − 14.23% and − 7.01% respectively. There are several possible explanations for the observed quick shrinkage of urban and rural construction land and tidal wetland. First of all, with the gradually increased utilization of tidal wetland and other unused land, some tidal wetland could be developed into aquaculture land or artificial wetland, which is also consistent with the current change trend of tidal wetland. Secondly, under the proposing of intensive and economical utilization of construction land, some abandoned industrial and mining land could be gradually reclaimed into usable garden land, forest land and other agricultural land. The single dynamic degree of farmland was the greatest in the ecological protection scenario. The result indicated that under this scenario, farmland decreased faster than the other two scenarios. This accelerated reduction of farmland area was probably due to the implementation of “Grain for Green Project” and “Grain for water Project”, and other ecological environmental protection measures. During 2017–2025, the area of projected subsided seeper also gradually reduced because of the advancement of land reclamation and the improvement of technology.

To further analyze the LULC change in 2025, the simulated LULC maps in three different scenarios and land use map in 2016 were subjected to raster calculation. The results are shown in Fig. 6 .

As shown in Fig. 6 and Table 6 , under the natural development scenario, some farmland concentrated in the east of Wanglou Village of Gaolou Township and surrounding areas, was projected to be converted to garden land or other agricultural land in 2025, due to its natural geological characteristics or adjustment of agricultural structure. Other farmland, located in the tributaries of Weishan Lake and surrounding areas southern to the secondary dam, was projected to be converted to water body, due to rainfall and resulting lake water level rise. The area of construction land in the south of Xiazhen Street and the north of Zhaoyang Street was projected to decrease, and it was mainly transferred into other agricultural land. Fucun Street has severe land subsidence and is close to lake. After reclamation, some of the subsided land with water accumulation was projected to be converted to water area. Tidal wetland was mostly predicted to be converted to other agricultural land or water area. Specifically, the large areas of tidal wetland, located in the east bank of Zhaoyang Lake and the north bank of Weishan Lake, were projected to be converted to water area, and a large area of tidal wetland in the north of Liuzhuang Town was projected to be converted to other agricultural land.

In the ecological protection scenario, the change of LULC types was similar to those in the natural development scenario. Urban and rural construction land and tidal wetland decreased the fastest. A large area of construction land in the east of Xiazhen Street and the middle of Zhaomiao Township was projected to be converted to other land. In this scenario, the reduction of construction land was faster than that in the other two scenarios, with -7.01% changing rate and total area reduction of 3434.58 ha. The tidal wetland was mostly to be converted to water body. In addition, the reduction of farmland was also faster in this scenario as compared with the other two scenarios, with an estimated changing rate of − 2.91% and a total area reduction of 4172.49 ha. The farmland was mainly converted to more ecological land types such as garden land and water area, due to the implementation of “Grain for Green Project ” and “Grain for water Project”. The subsided land with water accumulation also had a faster conversion rate in this scenario and was mostly to be converted to water area.

In this scenario, the reduction rate of farmland dropped significantly, with a small changing rate of -0.44% and a total area reduction of 629.73 ha. And in the northeast of Huancheng Town, some of the construction land was projected to be converted to farmland, which contributed to the farmland preservation. Both urban and rural construction land and tidal wetland showed deceasing trends, which are similar to those in the natural development scenario and the ecological protection scenario. However, the tidal wetland was projected to have the fastest changing rate in this scenario. A small proportion of tidal wetland located in the northern part of Huancheng Town was projected to be converted to farmland. Due to the effective farmland preservation measures, the changes of garden land and other agricultural land were significantly less in this scenario as compared with the other two scenarios. The change of water area in this scenario was similar to that and slightly slower than that in the natural development scenario, but significantly different from that in the ecological protection scenario. The subsided land with water accumulation changed in a similar decreasing trend in the three scenarios.

LULC changes under different scenarios from 2017 to 2025. Maps were generated using ArcGIS 10.1 for Desktop ( http://www.esri.com/software/arcgis/arcgis-for-desktop ).

Discussion and conclusion

In this study, the application of the CLUE-S model, combined with Markov model and BLRM, suggests that this method can reveal the driving factors of LULC change at a resolution of 60 m, and can effectively simulate the multi scenario of land use in the future. The results can guide the government to make more reasonable allocation of land resources in the mining area. In near future, in order to ensure the regional food supply security, Weishan’s government should enforce the management of farmland resources, especially high quality cultivated field, control the increase of construction land and implement the intensive and economical use of construction land. Meanwhile, the ecological LULC types, such as other agricultural land, water body and tidal wetland, should maintain a balanced proportion in the mining area. And the subsided land with water accumulation should be effectively reclaimed using appropriate technologies, in order to ensure the sustainable utilization of land resources and improve the ecological environment in the mining area.

However, due to the limitation of data acquisition, we should need to further improve the comprehensiveness of driving factors. Therefore, we should need to incorporate policies, measures, as well as other human factors in future research to better analyze the driving forces of land use dynamic changes. Markov model was used to predict the land use demand in the future in this study, we did not account for both random and systematic LULC transitions 47 . This is also what we need to further improve in the future study of LULC change.

In this study, using the CLUE-S model, combined with Markov model and BLRM, the spatial distribution pattern of LULC in 2025 under different scenarios was simulated and predicted. The characteristics of LULC change in 2025 are as follows:

(1) Under the three scenarios, the area of other agricultural land and water body which have regulatory effect on regional ecosystem showed an increasing trend; while the area of farmland, urban and rural construction land, subsided seeper area, and tidal wetland showed a decreasing trend, and the area of urban and rural construction land and tidal wetland decreased the fastest from 2017 to 2025. Under the ecological protection scenario, the decrease of farmland was faster than that in the other two scenarios. The projected area of subsided land with water accumulation also reduced gradually because of the advancement of reclamation.

(2) Under the natural development scenario, some farmland concentrated in the east of Wanglou Village of Gaolou Township and surrounding areas, was projected to be converted to garden land or other agricultural land. Some farmland, located in the tributaries of Weishan Lake and surrounding areas southern to the secondary dam, was projected to be converted to water body. Fucun Street has severe land subsidence and is close to lake. After reclamation, some of the subsided land with water accumulation converted to water body. Tidal wetland was mostly converted to other agricultural land or water body. The construction land was mainly converted to other agricultural land.

(3) Under the ecological protection scenario, the changes of LULC types were similar to the natural development scenario, but the change speed was faster than the other two scenarios. Among all LULC types, urban and rural construction land decreased the fastest. Farmland also decreased rapidly, and most of it converted to more ecological land such as garden land and water body. Under the farmland protection scenario, the tidal wetland decreased the fastest, followed by urban and rural construction land. Some construction land was projected to be converted to farmland, so that farmland would be effectively protected.

Malik, M. & Rai, S. C. Drivers of land usecover change and its impact on pong dam wetland. Environ. Monit. Assess. 191 , 203.1-203.14 (2019).

Article   Google Scholar  

Badamfirooz, J. & Mousazadeh, R. Quantitative assessment of land useland cover changes on the value of ecosystem services in the coastal landscape of anzali international wetland. Environ. Monit. Assess. 191 , 694.1-694.13 (2019).

Liu, M., Hu, Y., Chang, Y., He, X. & Zhang, W. Land use and land cover change analysis and prediction in the upper reaches of the Minjiang river, China. Environ. Manage. 43 , 899–907 (2009).

Article   ADS   Google Scholar  

Deng, Z., Zhang, X., Li, D. & Pan, G. Simulation of land useland cover change and its effects on the hydrological characteristics of the upper reaches of the hanjiang basin. Environ. Earth Sci. (2014).

Kabite, G., Muleta, M. K. & Awoke, B. G. Spatiotemporal land cover dynamics and drivers for Dhidhessa river basin (drb), Ethiopia. Model. Earth Syst. Environ. 6 , 1089–1103 (2020).

Miao, L. et al. Application of landuse change model in guiding regional planning: A case study in hun-taizi river watershed, Northeast China. Chin. Geogr. Sci. 21 , 609 (2011).

Basommi, L. P., QingFeng, G., DanDan, C. & Singh, S. K. Dynamics of land use change in a mining area: A case study of Nadowli district, Ghana. J. Mount. Sci. 13 , 633–642 (2016).

Kamga, M. A., Fils, S. C. N., Ayodele, M. O., Olatubara, C. O. & Khalifa, M. Evaluation of land useland cover changes due to gold mining activities from 1987 to 2017 using landsat imagery, East Cameroon. GeoJournal (2019).

Bürgi, M., Hersperger, A. M. & Schneeberger, N. Driving forces of landscape change: Current and new directions. Landsc. Ecol. 19 , 857–868 (2004).

Bai, J. H. et al. Landscape pattern evolution processes of alpine wetlands and their driving factors in the zoige plateau of china. J. Mount. Sci. 10 , 54–67 (2013).

Jing’An, S., Yongfeng, D., Wei, W. & Shichao, Z. Simulation of future land-use scenarios in the three gorges reservoir region under the effects of multiple factors. J. Geogr. Sci. 1 , 1907–1932 (2018).

Google Scholar  

Yongjiu, F. et al. Urban expansion simulation and scenario prediction using cellular automata: Comparison between individual and multiple influencing factors. Environ. Monit. Assess. 191 , 291 (2019).

Zhanqiang, Z., Liming, L., Zhantao, C., Junlian, Z. & Peter H., V. Land-use change simulation and assessment of driving factors in the loess hilly regio: A case study as pengyang county. Environ. Monit. Assess. (2010).

Gidey, E., Dikinya, O., Sebego, R., Segosebe, E. & Zenebe, A. Cellular automata and markov chain (ca-markov) model-based predictions of future land use and land cover scenarios (2015–2033) in raya, northern ethiopia. Model. Earth Syst. Environ. (2017).

Jahanishakib, F., Mirkarimi, S. H., Salmanmahiny, A. & Poodat, F. Land use change modeling through scenario-based cellular automata Markov: Improving spatial forecasting. Environ. Monit. Assess. 190 , 2–10 (2018).

Novin, M. S. & Ebrahimipour, A. Spatio-temporal modelling of land use changes by means of ca–Markov model. Model. Earth Syst. Environ. 5 , 1253–1263 (2019).

Wang, R., Ahmed, D. & Yuji, M. Spatiotemporal simulation of future land usecover change scenarios in the Tokyo metropolitan area. Sustainability 10 , 2056 (2018).

Abuelaish, B. & Olmedo, M. T. C. Scenario of land use and land cover change in the gaza strip using remote sensing and gis models. Arab. J. Geosci. 9 , 1–14 (2016).

Zhou, L., Dang, X., Sun, Q. & Wang, S. Multi-scenario simulation of urban land change in shanghai by random forest and ca-Markov model. Sustain. Cities Soc. 55 , 102045 (2020).

Li, Y. C. & He, C. Y. Scenario simulation and forecast of land usecover in Northern China. Chin. Sci. Bull. 1 , 1401–1412 (2008).

Huang, H. et al. Modeling the impacts of drying trend scenarios on land systems in Northern China using an integrated sd and ca model. Sci. China Earth Sci. 04 , 275–290 (2014).

Cheng, L., Sun, H., Zhang, Y. & Zhen, S. Spatial structure optimization of mountainous abandoned mine land reuse based on system dynamics model and clue-s model. Int. J. Coal Technol. 6 , 113–126 (2019).

Article   CAS   Google Scholar  

Fangyu, Z. & Yecui, H. Assessing temporal-spatial land use simulation effects with clue-s and markov-ca models in beijing. Environ. Sci. Pollut. Res. Int. (2018).

Miao, L. et al. Combining clue-s and swat models to forecast land use change and non-point source pollution impact at a watershed scale in Liaoning province, China. Chin. Geogr. Sci. 24 , 540–550 (2014).

Zare, M., Nazari Samani, A. A., Mohammady, M., Salmani, H. & Bazrafshan, J. Investigating effects of land use change scenarios on soil erosion using clue-s and rusle models. Int. J. Environ. Sci. Technol. (2017).

Guan, D., Zhao, Z. & Tan, J. Dynamic simulation of land use change based on logistic-ca-markov and wlc-ca-markov models: A case study in three gorges reservoir area of Chongqing, China. Environ. Sci. Pollut. Res. 26 , 1–3 (2019).

Weiguo, J., Zheng, C., Xuan, L., Kai, J. & Wu, Y. Simulating urban land use change by incorporating an autologistic regression model into a clue-s model. J. Geogr. Sci. 25 , 836–850 (2015).

Mei, Z., Hao, W. U. & Shiyun, L. I. Simulating land-use changes by incorporating spatial autocorrelation and self-organization in clue-s modeling: A case study in zengcheng district, guangzhou, china. Front. Mech. Eng. 12 , 299–310 (2018).

Haoran, H. et al. Characteristic analyses, simulations and predictions of land use in poor mountainous cities: A case study in the central area of Chengde county, China. Environ. Earth Sci. 77 , 1–10 (2018).

Sun, P. et al. Scenario simulation and landscape pattern dynamic changes of land use in the poverty belt around beijing and tianjin: A case study of Zhangjiakou city, Hebei province. J. Geogr. Sci. 26 , 272–296 (2016).

Article   ADS   CAS   Google Scholar  

Yecui, H., Yunmei, Z. & Xinqi, Z. Simulation of land-use scenarios for Beijing using clue-s and Markov composite models. Chin. Geogr. Sci. 23 , 92–100 (2013).

Huiran, H., Chengfeng, Y. & Jinping, S. Scenario simulation and the prediction of land use and land cover change in Beijing, China. Sustainability 7 , 4260–4279 (2015).

Li, S. H. Scenario simulation of land usecover change in Fuxian lake basin based on conversion of land use and its effects at small region extent model, Yunnan province, China. Appl. Ecol. Environ. Res. 17 , 1–10 (2019).

ADS   Google Scholar  

Verburg, P. H. Simulating feedbacks in land use and land cover change models. Landsc. Ecol. 21 , 1171–1183 (2006).

Verburg, P. H. et al. Modeling the spatial dynamics of regional land use: The clue-s model. Environ. Manage. 30 , 391–405 (2002).

Waiyasusri, K., Yumuang, S. & Chotpantarat, S. Monitoring and predicting land use changes in the huai thap salao watershed area, Uthaithani province, Thailand, using the clue-s model. Environ. Earth Sci. 75 , 533.1-533.16 (2016).

Yang, K., Liu, S., Wang, L., Yang, J. & He, D. An algorithm of spectral minimum Shannon entropy on extracting endmember of hyperspectral image. Guang pu xue yu guang pu fen xi 34 , 2229 (2014).

CAS   PubMed   Google Scholar  

Xu, L., Li, Z., Song, H. & Yin, H. Land-use planning for urban sprawl based on the clue-s model: A case study of Guangzhou, China. Entropy 15 , 3490–3506 (2013).

Bai, Y. P. & Wang, B. H. Study on regional land use structure change characteristics in baolan-lanqing-qingzang urban belt based on information entropy and regional entropy. Adv. Mater. Res. 518–523 , 6024–6029 (2012).

Fan, Y. et al. Entropies of the chinese land usecover change from 1990 to 2010 at a county level. Entropy 19 (2017).

Araya, Y. H. & Cabral, P. Analysis and modeling of urban land cover change in Setubal and Sesimbra, Portugal. Remot. Sens. 2 , 1549–1563 (2010).

De Habibza, H. P. On determining the most appropriate test cut-off value. Medica 26 , 297–307 (2016).

Pontius, R. Quantification error versus location error in comparison of categorical maps. Photogramm. Eng. Remot. Sens. 66 , 1011–1016 (2000).

Pontius, R. O. Statistical methods to partition effects of quantity and location during comparison of categorical maps at multiple resolutions. Photogramm. Eng. Remot. Sens. 68 , 1041–1050 (2002).

Biswas, M., Banerji, S. & Mitra, D. Land useland cover change detection and application of markov model: A case study of eastern part of kolkata. Environ. Dev. Sustain. 22 , (2019).

XiYong, H., Li, W., Xiao, L. & XiangHong, D. Effects of time-duration on the performance of the spatial-Markov model for land use change forecasting. J Indian Soc. Remot. Sens. 43 , 287–295 (2015).

Viana, C. & Rocha, J. Evaluating dominant land use land cover changes and predicting future scenario in a rural region using a memoryless stochastic method. Sustainability 12 (2020).

Download references

Acknowledgements

This work was supported by the grants of the research start-up fund of Shandong Agricultural University, the key technology research project of spatiotemporal pattern mining of rural geographic big data, the research project of smart Qihe biological big data resource platform. The authors would like to thank the anonymous reviewers and the editor for the very instructive suggestions that led to the much improved quality of this paper. Thanks for receiving the data from “ http://www.gscloud.cn/ ”.

Author information

Authors and affiliations.

College of Information Science and Engineering, Shandong Agricultural University, Tai’an, 271018, China

Xiaoyan Chang, Feng Zhang, Kanglin Cong & Xiaojun Liu

You can also search for this author in PubMed   Google Scholar

Contributions

Dr. X.C. conceived and designed the experiments, and guided the fundamental concept to the co-author. Dr. K.C. and Ms. X.L. performed the experiments and analyzed the data. Dr. X.C. wrote the main manuscript text. Dr. F.Z. reviewed the manuscript and put forward suggestions for revision.

Corresponding author

Correspondence to Feng Zhang .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Chang, X., Zhang, F., Cong, K. et al. Scenario simulation of land use and land cover change in mining area. Sci Rep 11 , 12910 (2021). https://doi.org/10.1038/s41598-021-92299-5

Download citation

Received : 01 February 2021

Accepted : 07 June 2021

Published : 18 June 2021

DOI : https://doi.org/10.1038/s41598-021-92299-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Multitemporal modeling and simulation of the complex dynamics in urban wetlands: the case of bogota, colombia.

• Yenny Cuellar
• Liliana Perez

Scientific Reports (2023)

Detection of peri-urban dynamicity in India: evidence from Durgapur municipal corporation

• Subrata Haldar
• Somnath Mandal

Asia-Pacific Journal of Regional Science (2023)

An integrated approach of logistic-MCE-CA-Markov to predict the land use structure and their micro-spatial characteristics analysis in Wuhan metropolitan area, Central China

• Haijun Wang

Environmental Science and Pollution Research (2022)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: Anthropocene newsletter — what matters in anthropocene research, free to your inbox weekly.

• Open access
• Published: 02 July 2014

GIS-based multi-criteria analysis for land use suitability assessment in City of Regina

• Jiapei Chen 1  

Environmental Systems Research volume  3 , Article number:  13 ( 2014 ) Cite this article

28k Accesses

Metrics details

Land use suitability assessment is a key factor in any urban and suburban planning and decision-making processes. The assessment is evaluated by a series of criteria involving socio-economic needs. To deal with the conflicting, disproportionate and multiple criteria, land usage will be characterized with respect to the preferences and importance. Meanwhile, many spatial decision problems can be typically analyzed and interpreted visually by applying GIS for mapping and analysis. Accordingly, this study is to introduce the Multi-criteria decision analysis into the land use suitability analysis along with the existing perspective evolving the role of GIS.

For case study, it is the first time to conduct the identification of the current land use situations in City of Regina by using GIS, combined with multi-criteria analysis ideology for existing condition analysis with three criteria referring to social and economic factors. Finally, the study identified five suitability levels, which has revealed the trends, challenges and prospects of land use analysis for urban extension in City of Regina.

Comparing the simulated land use suitable classes to the existing land use pattern, difference and optionality have been presented. The results are providing valuable information for the urban extension for policy and decision makers. To improve the accuracy and the reliability of the real-world case study, criteria selection and weight assignments ranks the first place. The integrated use of data analysis and Multi-criteria Decision Analysis approach, in a GIS context, resulted in a visible assessment of current land use in Regina.

Due to the increasing population and economic growth, human activities have continuous impacts on land use. Those impacts might lead to a series complexities toward environment and land resources development (Huang and Xia 2001 ). Issues related to population and land use competition has emphasized the need for more effective land use planning and policies. In Canada, in particular, the population has been projected to be 47.7 million by 2036 and 63.8 million by 2061, in comparison to 33.7 million in 2009. This pressure of the population will increase the requirement of land use enormously. Land use suitability assessment is to afford a reasonable and sustainable manner for land resource development. Meanwhile, the growing demand for urbanization, land resources used for a variety of purpose will interact and compete with each other. Rational and sustainable decision support based on the land use suitability assessment is an issue of great concern to governments and land users. Thus, an effective way to assess suitability of the current land use and provide policy support to the future land use is desired.

Previously, various methods of spatial analysis for land use are commonly used in the suitability assessment studies. The problem of land use suitability assessment have often been tackled using multi-criteria decision analysis (MCDA) since 1980s (Antoine et al. 1997 , Collins et al. 2001 , Kiker et al. 2005 , Sharifi et al. 2006 , Kunwar et al. 2010 ). Cheng et. al., has reported an integrated MCDA linear programming approach to support selection of an optimal landfill site (Cheng et al. 2003 ). To create visualized suitability map for users and decision makers, the integration of MCDA and GIS has been widely promoted for solving spatial problems in urban assessment and planning (Phua and Minowa 2005 ). (Malczewski 2006 ) conducted a survey of literature of the GIS-based Multi-criteria analysis from 1990 to 2004. There has been a substantial acceleration in the number of the GIS-MCDA articles published in this field. Joerin et al. ( 2001 ) put forward an outranking multi-criteria analysis method and output a set of land use suitability maps incorporating complex criteria integrating several stakeholders' points of view. Meanwhile, some case studies were performed using the method of integrating GIS and multi-criteria analysis. Hanyang lake area located in Wuhan city, China, was studied with this comprehensive method to analyze the suitability of future land use according to specified requirements, preferences and predictions in Yong Liu et al.’s research (Liu et al. 2007 ). Dai et al. ( 2001 ) conducted a study of the urban land use planning based on GIS and multi-criteria analysis method, which was applied in Lanzhou city, and its vicinity in north-western China.

However, the research has seldom focused on the Prairie Provinces in Canada, especially for the city with less proportion of population. For the further development and urbanization, the land use suitability assessment will play an important role. Thus, the primary aim of this study is to provide recommendation for integrated and sustainable plan for land use development referring to accessibility, economic, integration and environment by means of weighting the selected criteria. Since the required criteria are heterogeneous and measured on various scales in this method. In addition, the data is limited, this research will only analyze the current situation and future exploitation forecasting based on simplified factors, such as population and income.

The assessment is often assessed by a number of criteria. To deal with the inconsistent, incommensurate and multiple criteria, a comprehensive method is needed to analysis the land use scheme under current situation. Then it can be applied to the land use forecasting and planning. The individual criteria will be characterized with respect to the significance and preferences. Meanwhile, spatial decision problems can also be typically analyzed and demonstrated on the base of visualization. Accordingly, the study is to introduce the Multi-criteria decision analysis into the land use suitability analysis along with the existing perspective evolving the role of Geographical Information Systems (GIS).In this study, the existing land use situation was analyzed and evaluated. Then, based on the analysis the importance of each factor or criterion, the multi-criteria analysis system for land use suitability will be applied. Finally, comparison between the existing land use pattern and forecasting land use possibility of the same area will be conducted. The flowchart is shown in Figure  1 . Provided data sets in order to generate and store them in a GIS framework, while, as far as the last data sets are concerned, MCDA was involved in the calculation and acquisition in a GIS environment.

Flowchart of the study.

The study area

The study area is the City of Regina, located in southern Saskatchewan, Canada (as shown in Figure  2 ). The coordinate of the site is 50°27′17″N, 104°36′24″W. The area of the city is 118.87 km 2 . Total population of the study area was 179,246 according to census record in 2006. As the capital city of Saskatchewan, city of Regina ranks the second largest in the province, and is a cultural and commercial metropolis in southern Saskatchewan.The current land use map is presented in Figure  3 . There are eight main categories in this study area: Airport, Commerce, Industry, Resident, Institution, Open space, Railway, and Urban holdings. Figure  4 shows the proportion of different land use types. As see form the graph, most of the land in Regina is used as residential area, and then is the open space.

Location of study area and the Saskatchewan Canada.

Current land use pattern in Regina.

The current land use types and proportion in Regina.

It is reported that strong economic growth has led to employment and population growth in the Population, Employment and Economic Analysis of city of Regina. Thus population, employment and income are chosen as social and economic effect factors. The data source and information are obtained from TerraServer of TERRA Lab, website of Bureau of Saskatchewan and Canada Statistics. On the basis of “A Guide to the Municipal Planning Process in Saskatchewan”, a comprehensive policy framework to guide physical, environmental, economic, social, and cultural development in municipality is provided. As social development is one of the most important factors in land use planning, it is considered separately. The data that will be used in the multi-criteria analysis would be related to population, average income of particular census, and employment.

Multi-Criteria Decision Analysis (MCDA), developed in the environmental of Operation Research, aids analysts and decision-makers in situations in which there is a need for identification of priorities according to multiple criteria. This usually happens in situations where conflictive interests coexist (Gomes and Lins 2002 ). MCDA can incorporate both geographical data and stakeholders’ preferences into quantified values for assessment and further decisions (Malczewski 2004 ). The GIS analysis, if integrated with a procedure of data analysis and structuring, can be usefully developed when data are available but the decision context cannot indicate how these data have to be used to produce information and support decisions. The GIS support the solution of complex spatial problems, providing the decision-maker with a flexible environment in the process of the decision research and in the solution of the problem. The visualization of the context, structure of the problem and its alternative solutions is one for the most powerful components of a decision support system (Gomes and Lins 2002 ). Thus the integration GIS-MCDA has the objective of the supporting decision-makers, providing them with ways to evaluate several alternatives, based on multiple, conflictive criteria.

GIS is a set of tools for inputs, storage and tetrieval, manipulation and analysis, as well as outputs of spatial data (Malczewski, 1999 ). ArcGIS is acknowledged to be a powerful tool in solving the spatial problems. ArcGIS by ESRI GIS and mapping software was applied for spatial data analysis and mapping in this study. All the related data were collected from Terrasever and Terra lab at University of Regina. Land-use maps and administrative information were input into GIS digitally to establish a new geo-database, then overlapped with each other.

Meanwhile, policy analysis based on community plans and literature reviews were completed, serving as foundation for land use type categories. According to available data, land use for human activity were divided into five suitability levels. In this process, multi-criteria analysis method was used for classifying and weighing criteria. Quantitative analysis is necessary for multi-criteria analysis, including scoring, ranking and weighting.

Finally, an output map of the land use suitability with five classes was displayed and a comparison was conducted between the new land use pattern and the pre-existing land use status. The Halme et al. approach introduces the decision-maker’s preference in the efficiency analysis, by explicitly locating his most preferred solution vector on the efficient frontier.

The same authors highlight that when systematically exploring the neighborhoods of the Most Preferred Solution (MPS), one does not know explicitly the decision-maker’s value function, but its form becomes known when the end of the search for MPS is reached.

Weight product

Weight product (WP) method has been introduced centuries ago and been advocated in the past few years. WP is a relative simple multiple attribute utility methods. Since WP is easily understood by decision makers and is easy to be conducted, this method have been widely applied in many fields. In this study, based on the WP method, three factors including population, employment and average income, hold significance in municipal land use planning. In the multi-criteria analysis process as showed in Figure  5 , they were assign different weight to obtain a total score of every region based on the following formula (Gomes and Lins 2002 ):

The Multi-criteria Analysis Process.

Where W j --- is weight of each criterion j = 1,2,….m,

And A i ---is the normalize the value of each grid cell, i = 1,….., n.

The general MCAD approach for this case may be seen in (1), where X i , Y i ,…, represent the value of the criterion X, Y…, for the alternation i; λ are the decision variables that represent the decision-maker’s preferences for the alternative i, i = 1,…,n. For this case study, λ vector representing the decision maker preferences.

Defining the criteria

The expansion of land has overwhelmingly been a response to fast-rising population decades ago, so population is considered the most essential drive force of land exploitation. The weight of each criterion has been shown in Table  1 . Meanwhile, as the increasing of urban population, the urbanization of Regina fringe is an inevitable trend. Study of population can not only help analysis the existing land use pattern, but also assist land use trend forecasting. Based on the above-mentioned consideration, that population is specified the maximum weight among the criteria. The population distribution of Regina is shown in Figure  6 .The employment is expanded to labor force, which is in turn expanded to population equivalents. From a land use point of view, although a city or a region is usually studied as a whole, it is also necessary to examine employment changes brought about by changes in economic. Therefore, employment is defined as a factor in the process of land use or land development. The employment situation of Regina is showed in Figure  7 .

The population distribution of Regina.

The employment situation of Regina.

Furthermore, as like Hok Lin Leung mentioned that income investigate is essential in house marketing, income is equivalent important in land use planning. The income census of a certain area can reflect the consumption level and trend in a certain extent (Leung 2003 ). Thus, as one of the economic factor, income is also taken into account when it comes to the land use suitability assessment. The average income of a certain census tract in Regina is showed in Figure  8 .

The average income of census.

Results and discussion

After the spatial analysis through ArcGIS, a land use suitable level map was obtained. In this map, the suitability of land use was divided into 5 classes (shown in Figure  9 ). The most suitable level was defined as the highest score among the weighted values, marking red in the legend. The red areas are in high rate of employment, as well as high income with large population, so they are capable for more human activities area like commercial and residential regions. On the contrary, the least suitable areas were defined to be more suitable for open sources, since there are less human beings and low income or benefit. Based on this interpretation, it could be predicted that the development tendency of Regina would be at north-west and south-east part of the city.

The land use suitability assessment output.

Meanwhile, the current land use map is jointed into the suitability assessment output (Figure  10 ). Comparison is conducted between these two land use patterns in Table  2 . As shown in Table  2 , there is a significant distinction between the simulated land use and the actual land use pattern. The results shows that there are significant difference between the simulated land use availability and the existing land use conditions. Although we can say it is not an ideal plan, we can still find and learn something faulty from the process of analysis and make it available to improve in the next time.

The comparison between current land use pattern and simulation.

In the study, the priority is the criteria selection and determination. In real-world case study, a large number of criteria should be determined, referring to environment, ecology, social and economic. Whilst in this research, only economic factor were considered. This can be considered as a single stage test of the complicated land use plan procedure. Moreover, the weight of criteria should be determined by both experts and stakeholders. In this research, the weight was just determined by literal evaluation from municipal land use project plan.

Secondly, the simulation of suitable level is simplified, whilst in the real world, the development pattern is complicated. In the analysis, development scenarios in land use are not easy to pin down. There are no universal rules as to what they should or should not include, and there are no tools available to generate them automatically. F.C. Dai et al. set two scenarios in their study of urban fringe land use planning. One is mainly based on the actual development simulation, and the other scenario is mainly depended on the government planning. Thus, setting scenarios might increase the accuracy of the simulation as well as the reliability.

Moreover, as it is under a small scale analysis, the simplified definition is considered to be acceptable. However, the definition of suitability level results in unprofessional. Take the black spot in the least suitable level for example. It is hard to explain its appearance. It might be assumed to be the fault in the multi-criteria analysis procedure. And beyond the public opinion survey and social investigation, the suitability assessment seems to be groundless. Thus, the result might be better if the operational research is implemented in the future study.

Assessing the land use development problem has become an important task under the increasing aware of land resource conservation. Land use suitability assessment is a practical tool to make decision on land use development. However, less works could be found that use quantized index to evaluate the land resource usage at Prairie Provinces in Canada. This study applied GIS combined with multi-criteria decision analysis ideology in the City of Regina to assess land use condition with three important criteria referring to social and economic. Finally, a map with five suitability levels can be obtained.

When comparing the simulated land use suitable classes with the existing land use pattern, we can find that: the significant differences between these two land use patterns reflect the limitation of the approach and data availability. Two possibilities are put forward to increase the reliability and accuracy of land use suitability assessment, where the research is potentially valuable. Urban land use categories are complicated process. Recommendations made for future studies is to improve the efficacy and objectivity of local land use evaluation to support the land use suitability assessment and avoid the subjectivity. As for the accuracy of the real-world case study, the criteria selection and the weight assignment should be widely and deeply discussed and researched.

The results represent the potential of GIS-based evaluation for urban planning purpose. However, it needs to be emphasized that the reliability of the assessment results depends on a multitude of factors ranging from the quality of the database to the potential errors in the GIS. Meanwhile, the modeling results are highly significant to the weights applied. The determination of a multitude of factors and weights for the various factors is one of the most important challenges in the future.

Author’s contributions

JC carried out the data collection, methods, results analysis and finish the manuscript.

Antoine J, Fischer G, Makowski M: Multiple criteria land use analysis. Appl Math Comput 1997, 83: 195–215.

Article   Google Scholar  

Cheng S, Chan CW, Huang GH: An integrated multi-criteria decision analysis and inexact mixed integer linear programming approach for solid waste management. Eng Appl Artif Intel 2003, 16 (5):543–554.

Collins M, Steiner F, Rushman M: Land-use suitability analysis in the United States: historical development and promising technological achievements. J Environ Manage 2001, 28 (5):611–621. 10.1007/s002670010247

Dai F, Lee C, Zhang X: GIS-based geo-environmental evaluation for urban land-use planning: a case study. Eng Geol 2001, 61 (4):257–271. 10.1016/S0013-7952(01)00028-X

Gomes E, Lins M: Intergrating geographical information systems and multi-criteria methods: a case study. Ann Oper Res 2002, 116: 243–269. 10.1023/A:1021344700828

Huang G, Xia J: Barriers to sustainable water-quality management. J Environ Manage 2001, 61: 1–23. 10.1006/jema.2000.0394

Joerin F, Thériault M, Musy A: Using GIS and outranking multicriteria analysis for land-use suitability assessment. Int J Geogr Inf Sci 2001, 15 (2):153–174. 10.1080/13658810051030487

Kiker G, Bridges T, Varghese A, Seager T, Linkov I: Application of multicriteria decision analysis in environmental decision making. Integr Enviro Assess Manage 2005, 1 (2):95–108. 10.1897/IEAM_2004a-015.1

Kunwar P, Kachhwaha T, Kuma A, Agrawal AK, Singh A, Mendiratta N: Use of high-resolution IKONOS data and GIS technique for transformation of landuse/landcover for sustainable development. Curr Sci India 2010, 98 (2):204–212.

Google Scholar  

Leung H: Land use Planning Made Plain . University of Toronto Press, Toronto, Canada; 2003.

Liu Y, Lv X, Qin X, Guo H, Yu Y, Wang J, Mao G: An integrated GIS-based analysis system for land-use management of lake areas in urban fringe. Land Scape Urban Plan 2007, 82 (4):233–246. 10.1016/j.landurbplan.2007.02.012

Malczewski J: GIS and multicriteria decision analysis . John Wiley & Sons; 1999.

Malczewski J: GIS-based land-use suitability analysis: a critical overview. Pro Plann 2004, 62 (1):3–65. 10.1016/j.progress.2003.09.002

Malczewski J: GIS‒based multicriteria decision analysis: a survey of the literature. Int J Geogr Inf Sci 2006, 20 (7):703–726. 10.1080/13658810600661508

Phua M, Minowa M: A GIS-based multi-criteria decision making approach to forest conservation planning at a landscape scale: a case study in the Kinabalu Area, Sabah, Malaysia. Land Scape Urban Plan 2005, 71 (2):207–222.

Sharifi M, Boerboom L, Shamsudin K, Veeramuthu L: Spatial Multiple Criteria Decision Analysis in Integrated Planning for Public Transport and Land use Development Study in Klang Valley, Malaysia . ISPRS Technical Commission 2nd Symposium, United States; 2006:85–91.

Download references

Acknowledgement

This research has been conducted within University of Regina. The Terrasever and Terra lab provided the equipment and materials for this research. This research is also supported by Dr. Joe Piwowar in the data collection and Dr. Gordon Huang.

Author information

Authors and affiliations.

Faculty of Engineering and Applied Science, University of Regina, S4S 0A2, Regina, SK, Canada

Jiapei Chen

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Jiapei Chen .

Additional information

Competing interests.

The author declares that she has no competing interests with anyone.

Authors’ original submitted files for images

Below are the links to the authors’ original submitted files for images.

Authors’ original file for figure 1

Authors’ original file for figure 2, authors’ original file for figure 3, authors’ original file for figure 4, authors’ original file for figure 5, authors’ original file for figure 6, authors’ original file for figure 7, authors’ original file for figure 8, authors’ original file for figure 9, authors’ original file for figure 10, authors’ original file for figure 11, authors’ original file for figure 12, authors’ original file for figure 13, authors’ original file for figure 14, authors’ original file for figure 15, authors’ original file for figure 16, authors’ original file for figure 17, authors’ original file for figure 18, authors’ original file for figure 19, authors’ original file for figure 20, rights and permissions.

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article.

Chen, J. GIS-based multi-criteria analysis for land use suitability assessment in City of Regina. Environ Syst Res 3 , 13 (2014). https://doi.org/10.1186/2193-2697-3-13

Download citation

Received : 12 December 2013

Accepted : 11 March 2014

Published : 02 July 2014

DOI : https://doi.org/10.1186/2193-2697-3-13

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Land use suitability
• Multi-criteria decision analysis
• Urban extension

• Open access
• Published: 14 March 2024

Assessment of land use land cover change and its effects using artificial neural network-based cellular automation

• Nishant Mehra   ORCID: orcid.org/0000-0001-6069-8103 1 &
• Janaki Ballav Swain 1  

Journal of Engineering and Applied Science volume  71 , Article number:  70 ( 2024 ) Cite this article

1269 Accesses

4 Citations

Metrics details

The challenge of urban growth and land use land cover (LULC) change is particularly critical in developing countries. The use of remote sensing and GIS has helped to generate LULC thematic maps, which have proven immensely valuable in resource and land-use management, facilitating sustainable development by balancing developmental interests and conservation measures. The research utilized socio-economic and spatial variables such as slope, elevation, distance from streams, distance from roads, distance from built-up areas, and distance from the center of town to determine their impact on the LULC of 2016 and 2019. The research integrates Artificial Neural Network with Cellular Automta to forecast and establish potential land use changes for the years 2025 and 2040. Comparison between the predicted and actual LULC maps of 2022 indicates high agreement with kappa hat of 0.77 and a percentage of correctness of 86.83%. The study indicates that the built-up area will increase by 8.37 km 2 by 2040, resulting in a reduction of 7.08 km 2 and 1.16 km 2 in protected and agricultural areas, respectively. These findings will assist urban planners and lawmakers to adopt management and conservation strategies that balance urban expansion and conservation of natural resources leading to the sustainable development of the cities.

Introduction

The demographic projections suggest that the Central and Southern Asia are poised to emerge as the world’s most populous region by 2037 [ 1 ]. Furthermore, India surpassed China to become the most populous country in the year 2023, and prevailing indications anticipate the persistence of this demographic trend for several decades [ 2 ]. The unrestrained expansion of built-up areas is majorly propelled by a substantial increase in population which ultimately leads to land use land cover (LULC) changes [ 3 , 4 , 5 ].

The significant characteristics of urban sprawl are a rapid decrease in vegetated areas [ 6 , 7 ], random and unplanned growth [ 8 , 9 ], increased economic activities in higher elevations [ 10 , 11 , 12 ], land cover change in agricultural areas [ 13 , 14 , 15 , 16 ], and increase in urban heat island [ 17 , 18 , 19 ]. This has created environmental, ecological, economic, and social challenges [ 8 ]. The changes, geographical and climatic, occurring in Himalayan cities call for special attention due to the geo-morphological, topographical, and seismic constraints [ 7 , 10 , 20 , 21 ]. Thus, the monitoring of spatio-temporal expansion of the cities and accurate prediction of LULC change is vital for ecosystem conservation and sustainable development management strategies to be implemented in these regions [ 22 ]. As per the year-wise records shared by the Department of Economics and Statistics, State Government of Himachal Pradesh in India, the class III cities having a population of less than 50,000 in the state were found to be more vulnerable to urban sprawl due to saturation in capital city Shimla, and thus, there is a pressing need to balance economic development with sustainable environmental practices.

The integrated use of remote sensing and GIS has helped immensely in the management of land and natural resources and in understanding the complex linkages between spatial patterns and processes responsible for change [ 7 , 23 , 24 , 25 ]. Thus, the modeling and accurate prediction of urban sprawl has been inviting the attention of various researchers [ 26 , 27 ], and the use of modern self-learning algorithms has further improved the accuracy of these models [ 28 , 29 , 30 , 31 ]. The understanding of dynamic changes occurring in the region and the incorporation of driving factors also improves the accuracy of these models [ 26 ].

Cellular automata (CA)-based models are spatially explicit models (SEM) that work on a simple premise that the future state of a land cover type is dependent on the past local interactions between the different land covers [ 22 , 26 ]. The model’s popularity in GIS grew immensely in the 1980s, catalyzed by pivotal contributions from Wolfarm [ 32 ], Michael Batty and Xie [ 33 ], and Batty et al. [ 34 ]. The accuracy of the model was dependent upon the temporal scale of maps, neighboring cells, and transition rules [ 35 , 36 ]. Batty [ 34 ], Leao [ 37 ], and Lagarias [ 38 ] found them to be powerful spatial dynamic models. The open structure, simplicity, good spatial resolution, and integration with other knowledge-driven models make it an appropriate choice for urban sprawl studies [ 22 , 26 , 35 , 39 ]. However, the model is dependent upon spatial data only and is limited in implementing driving forces which is important for complex processes and accurate simulation [ 22 , 26 ]. The non-uniform cell space, dynamic neighborhood classes, and non-stationary transition rules offer opportunities for modification in the original CA structure to make it applicable for real-time complex urban sprawl studies [ 22 , 35 ]. This makes it necessary to integrate CA with other models.

To address the inherent constraints in the individual models, various researchers have employed hybrid models like CA–Markov model [ 40 ] and CA-ANN model [ 41 ]. The integration of spatial patterns with the processes responsible for causing changes in landforms is imperative for the accurate prediction and modeling of land cover changes [ 24 ]. Artificial neural networks (ANN) can identify and analyze the complex inter-relationship between causative factors and complex patterns [ 26 , 42 ]. The architecture of ANN simulates and behaves in a similar pattern as the human brain and nervous system [ 43 , 44 , 45 ]. ANN can deal with incomplete data, does not assume the distribution of input data, and can detect potential inter-dependencies between driving factors [ 46 , 47 ]. Multi-layer perceptron (MLP)-ANN, consists of input layers, hidden layers, and an output layer, and is the widely used model in ANN because it is fast, accurate, and can infer and forecast outcomes derived from inputs that it has not encountered previously, exhibiting the capacity for extrapolation and prognostication [ 48 ]. Researchers have adeptly employed CA-ANN models to address spatial-dynamic complexities and driving factors, enhancing the robustness and realism of modeling for accurate prediction and estimation of land cover changes [ 18 , 39 , 42 , 49 , 50 ].

The study aims to model LULC change using MLP-ANN and cellular automation simulation in the city of Dharamshala, one of the fastest-growing cities in the state of Himachal Pradesh, India. The results are expected to act as a road map for urban planners and policymakers for sustainable development of the city. The research used the MOLUSCE plugin, as a tool to predict and assess the transformations occurring in each LULC type in the study area. In the study, LULC maps of 2016 and 2019 were used as independent variables in the model to simulate and validate the LULC map of 2022, and thereafter, LULC maps of 2025 and 2040 were predicted.

The research locale encompasses Dharamshala, situated in the state of Himachal Pradesh, India, as illustrated in Fig.  1 . Positioned within the Western Himalayas, the city graces the southern inclines of the principal regional Dhauladhar mountain range (V. Gupta et al., [ 51 ]). Geographically, the study vicinity spans from 32° 9′ 52″ N to 32° 15′ 58″ N in latitude and 76° 17′ 22″ E to 76° 23′ 09″ E in longitude, encompassing an expanse of 42.7 km 2 . Elevation within this area exhibits variability, ranging from 790 m in the southwest to an altitude of 2130 m above mean sea level (AMSL) in the north. The region has a humid subtropical climate and experiences a mean annual temperature of about 19.1 ± 0.5 °C. The zenith of temperature occurs in June with an average of 32 °C, while the nadir registers in January with an average of 10 °C. The northern parts of the region also receive heavy snowfall during winter. Geologically, the region forms a part of the Outer Himalayas with a predominant geological composition comprising sandstone, characterized by alternating bands of clays, shale, and siltstones (V. Gupta et al., [ 51 ]).

Study area, Dharamshala city

The city is the winter capital of the state of Himachal Pradesh and the headquarters of the Central Tibetan Administration. The city is a famous hill station destination, both for national and international visitors. Further, it is also the administrative headquarters of Kangra district. The city was declared a municipal corporation in the year 2015 by merging 9 adjacent villages and has ever since witnessed rapid urbanization. It is one among the 100 cities in India and the only city in the state of Himachal Pradesh chosen in the year 2016 to be developed under the National Smart Cities Mission by the Government of India.

A dramatic rise in urban spaces has been witnessed in the city from the year 2016 onwards, and there exists an inherent imperative to address the recent alterations that have manifested within this geographical area through a scientific lens. The time scale chosen in the study corresponds to the maximum socio-economic changes occurring in the city due to the formation of municipal limits, hosting of international cricket matches and also serving as the residence of His Holiness Dalai Lama.

The simulation’s correctness is determined by the quality of the data and criteria used in the investigation [ 26 , 35 , 39 ]. The month of May is characterized by sunny days with no or little rainfall in the region; thus, all the temporal satellite imageries were chosen from this month to negate the impacts of phenological effects and cloudy pixels [ 52 ]. The ancillary data included a draft town and country planning (TCP) report of Dharamshala city and ground truth points (using GPS) for assistance and validation in image classification.

The study incorporated LULC maps of 2016, 2019, and 2022 and digital elevation model (DEM), the details of which are given in Table  1 . Multi-temporal Landsat 8 Operational land Imager (OLI) satellite imageries for the years 2016, 2019, and 2022 were used, the description of which is shown in Table  2 . A hybrid approach involving a Maximum Likelihood Classifier (MLC) and thereafter adopting post-classificaton improvement measures using vegetation indices was used in the research study to create LULC maps of 2016, 2019, and 2022 with each LULC map attaining an overall accuracy surpassing 85% and kappa hat showing substantial agreement. The selection of the Maximum Likelihood Classifier was based on the topographical challenges and spectrally homogeneous attributes of the land cover classes under investigation. The correction of the land cover classes through visual interpretation becomes essential by utilizing high-resolution satellite imagery obtained from Google Earth and Planet Scope [ 53 , 54 ].

The riverine sources, in this part of the Himalayan region, are characterized by the presence of boulders and cobbles, and thus, the chances of overlapping spectral characteristics for the built-up areas and water bodies were likely. The Strahler order algorithm available in SAGA was used to accurately delineate the water bodies.

Various researchers have included slope, elevation, and aspect, as geospatial parameters; population density as the socio-economic parameter; and spatial variables such as distance from the water bodies, roads, built-up areas, and from the center of town for simulation [ 18 , 30 , 31 , 39 , 42 , 49 , 50 ]. After checking different combinations of socio-economic and physical factors, the simulated LULC map of 2022 showed the best performance by considering five parameters that included slope, distance from streams, distance from roads, distance from built-up areas, and distance from the center of town. The explanatory maps having the shp data format were converted to a raster and then Euclidean distance was calculated in QGIS to create a raster data type. The explanatory maps in GeoTIFF format were also created using Euclidean distance in QGIS.

The methodological workflow for the area under investigation is summarized in Fig.  2 . The MOLUSCE plugin available in QGIS 2.18 was used for the simulation of land cover change in 2022.

Methodological workflow and data analysis

The transition probabilities derived from MLP-ANN learning processes are fed into CA to predict and estimate the LULC changes in this hybrid model of CA-ANN [ 31 , 49 ].

Image pre-processing

The satellite imageries of 2016, 2019, and 2022 were transformed to spectral radiance values, and the Dark Object Subtraction (DOS) in the semi-automatic classification (SCP) plugin in QGIS was used for performing atmospheric correction. Thereafter, the images were mosaicked, and an image subset was performed using the shapefile of the municipal corporation limits of Dharamshala city. The shape file of municipal limits was geometrically corrected with the use of ground control points (GCP) selected using GPS. This was executed in a manner that ensured the Root mean Squared Error (RMSE) attained a value of less than half of a pixel [ 55 ].

Modified Anderson’s LULC classification system was adopted to produce thematic maps comprising five LULC classes, Protected areas (PA), Agricultural areas (AA), Built-up Areas (BA), Barren land (BL), and Water bodies (WB), as shown in Table  3 , for the years 2016, 2019, and 2022. Supervised classification using MLC was used for the creation of the five land cover classes [ 7 , 20 , 53 , 56 , 57 ]. The forests are protected under Indian Forest Act, 1927, and the tea plantations are protected under Himachal Pradesh Ceiling on Land Holdings Act, 1972, and thus were classified under the protected areas (PA).

The LULC maps for 2016 and 2019 are taken as input and establish the spatio-temporal dynamics of the region. The MOLUSCE plugin was used to create a transition map between 2016 and 2019 showing the percentage change occurring in each of the five land cover types for the period from 2016 to 2019.

For using the CA model, the region should be a discrete grided area, with each cell specifying a land cover type. The driving factors could be categorized as having different spatial attributes, such as distance parameters, physical properties, and neighborhood relationships [ 58 ]. The distance parameter includes distance from the streams, roads, built-up areas, and from the center of town. Physical properties include slope and elevation. Neighborhood relationships involve the percentage area of a land cover type around the cell of interest. The explanatory maps are extracted in a raster format (Fig.  3 ).

Explanatory map: slope, distance from streams, distance from roads, distance from built-up areas, distance from the center, and elevation

The transition functions are non-linear and represent the relationship between driving factors and transformation probabilities of land cover type [ 26 , 39 ]. ANN model is trained on explanatory maps, and then the transition probabilities are established for the CA model. The prediction of transition probabilities from the current land use type to different LULC categories at the subsequent time point, denoted as “ t  + 1,” was determined by taking into account the current LULC classification of a specific cell as well as the neighboring cells at time t .

Based on spatio-temporal dynamics and the impact of driving factors, the simulation is initially performed for the year 2022, and based on the performance of the model, the predictions are thereafter made for the years 2025 and 2040 in the iterative steps of two and six, respectively, in the model.

Evaluating correlation and transition analysis

The examination of correlation among the driving factors was executed using the Cramer coefficient, also known as the Cramer V method, particularly suitable for contingency tables larger than 2 × 2. The outcomes span a range of 0 to 1, where elevated values signify a heightened correlation amid the driving factors. A coefficient surpassing 0.15 indicates a substantial explanatory potency of variables [ 49 ]. The correlation matrix is shown in Table  4 .

The changes (in area and percentage) occurring in the land cover classes for the period 2016 to 2019 are shown in Table  5 . The transition matrix, shown in Table  6 , helps compare and understand temporal transformations occurring in the region, without the impact of physical and socio-economic driving factors. Within the matrix’s diagonal, the constituent elements signify the magnitude of class constancy, portraying the persistence of specific land cover categories. Conversely, the off-diagonal entries encapsulate the dimensions of shifts occurring between distinct classes [ 18 ]. The values proximate to 1 are present in the diagonal entries, signifying the stability of the corresponding land cover types for the chosen period.

Transition potential modeling

The transformations occurring in a region are a highly complex process dependent on spatio-temporal changes and driving factors responsible for the changes [ 26 , 31 ]. The geographical phenomenon although non-linear and stochastic but have fractal properties [ 59 ] and machine learning algorithms, like MLP-ANN, can be very useful in the identification of these changes [ 45 , 60 ]. The transition function pertaining to the alteration in LULC delineates the association linking the driving factors with the probabilities of conversion, specifically discerning whether cells will shift towards a particular land use/cover classification. The multi-layer feed-forward approach of the model is trained using the error back propagation, wherein the network parameters are modified as per the output error demands [ 48 , 58 , 61 ]. The learning curve for the ANN-MLP is shown in Fig.  4 .

Neural network learning curve

In LULC simulation, the cross-tabulation matrix, also referred to as a contingency table, error matrix, or confusion matrix, stands as an extensively utilized approach for the evaluation of outcomes [ 62 ]. Cross-tabulation facilitates a comparative analysis between the outcomes projected by the model and the observed outcomes [ 63 ]. In this matrix, each row corresponds to the anticipated category, while each column signifies the factual category, thereby showcasing discrepancies in the cells, often expressed as errors represented in percentages or areas [ 27 , 64 ].

The assessment of accuracy was conducted utilizing overall accuracy and kappa hat statistics as the metrics of evaluation. Both metrics use the confusion matrix for calculation purposes. The determination of overall accuracy involves the consideration of diagonal elements only within the confusion matrix, while the kappa hat also considers non-diagonal elements and thus incorporates omission and commission errors [ 64 ]. Kappa hat evaluates the land modeling performance excluding chance agreement [ 65 ], with values ranging from 0.41 to 0.60 categorized as “moderate agreement” and 0.61 to 0.80 as “substantial agreement” [ 27 , 66 ].

Several simulations with different combinations of exploratory maps were performed, as shown in Table  7 . The combination consisting of the parameters distance from built-up areas, distance from roads, distance from the center of town, elevation, slope, and distance from streams showed the maximum accuracy and was chosen in the research study to prognosticate the LULC for the year 2022. The simulated and actual maps were compared with the accuracy metric kappa having a value of 0.77 denoting a notable concordance between both the maps and accuracy was found to be 86.83%. It can be concluded from these that the explanatory variables chosen had a great influence on the prediction of LULC classes. The maps for the years 2025 and 2040 were predicted after running two and seven iterations in CA, respectively.

Results and discussion

The LULC distribution for the years 2016, 2019, and 2022 is shown in Table  8 . Table 9 shows the transition undergoing area-wise and percentage-wise for each LULC class from 2016 to 2019 and 2019 to 2022. The positive values show the increase in that land cover class, while the negative values indicate the decrease for a particular land cover class. The spatio-temporal distribution of LULC classes for the years 2016, 2019, and 2022 are shown in Fig.  5 . It can be observed that protected areas had undergone the maximum transition from the year 2016 to 2022 with a reduction of 11.85% and a decrease of 5.04 km 2 in area. The built-up areas had increased considerably by 14.54% and 6.18 km 2 in area. The agricultural areas had also decreased by 2.73% and 1.16 km 2 in area and a slight increase in barren land is also observed. This signifies the impact of anthropogenic and socio-economic activities in the city and the rapid conversion of this hill station into a concrete jungle. The results also indicate widespread encroachments and abeyance of legislation.

LULC maps for the years 2016, 2019, and 2022

The increase in built-up areas and barren land for the period 2016–2022 is primarily related to the increasing human population and tourist inflow in the city, leading to additional need for residential and commercial spaces. This led to high pressure on the protected areas and agricultural areas, which had suffered maximum depreciation for this period.

The region lying at an altitude of less than 1500 m remained the most critical with maximum changes in LULC classes being witnessed there. The built-up areas, agricultural areas, and protected areas showed maximum transition in this region. The main reason for this could be attributed to the better transportation facilities, road connectivity, suitable climatic conditions for living and agricultural practices, commercial establishments, and more population concentration in this region. Higher altitude regions, because of terrain and other geographical constraints, are less vulnerable to built-up areas. Thus, the city requires greater concern and attention from policymakers and environmentalists to pave the way for a balanced, holistic, and sustainable development model.

The simulation and accurate prediction of LULC become necessary to understand the trend and direction of urban sprawl. The LULC maps of 2025 and 2040 were prepared using CA modeling, and the spatial distribution of these LULC maps is shown in Fig.  6 . Six driving factors, distance from built-up areas, distance from roads, distance from the center of town, elevation, slope, and distance from streams, were chosen for the modeling.

Predicted LULC maps for the years 2025 and 2040

The LULC change analysis of the maps from 2016 to 2025 and 2016 to 2040 is shown in Tables  10 and 11 . The results indicate the continuation of the trend of increase in the built-up areas and a decrease in protected areas for the year 2025. However, the increase in built-up areas will saturate after 2025, and the percentage increase in built-up areas for 3 years will be reduced as compared to the previous 3-year transition. This could be attributed to the fact that most of the usable and productive areas for construction will be exhausted.

The hilly areas offer geographical and topographical constraints for construction, and thus, the ideal locations for construction are usually those located at mid-altitudes and having less slope. The seismicity of the area is another challenge. All these factors will lead to construction in high seismic and landslide-prone areas, which would present a significant impediment to the well-being and security of the inhabitants. Another important observation from the findings was that the transition of built-up areas on the temporal scale is usually restricted to mid and south-eastern regions of the study area. The region has witnessed urban sprawl in these pockets and will remain a critical region in the future.

The swift expansion of urbanized regions, stemming from demographic expansion and the influx of tourists, emphasizes the critical significance of implementing sustainable urban planning strategies. Effective land-use management strategies should be implemented by policymakers and urban planners involving the promotion of efficient land use, reducing urban sprawl, and preserving green spaces, contributing to the attainment of Sustainable Development Goal (SDG) 11, which focuses on creating sustainable cities and communities.

The decline in protected areas is a matter of concern as it poses a threat to biodiversity and ecosystems. Strict implementation of legislation, with the involvement of environmentalists and policymakers, can help protect and restore these areas, thus preserving biodiversity and ensuring the long-term sustainability of natural resources. This effort directly relates to SDG 15, which focuses on maintaining and enhancing life on land.

Land-use planning plays a crucial role in fostering responsible consumption and production patterns. By optimizing land use and preventing further encroachment on protected areas, policymakers can contribute to sustainable resource management and reduce the environmental impact of human activities, which aligns with the objectives of SDG 12, aiming to ensure responsible consumption and production.

The increasing population and tourists will remain the major driving factors for the change. The decrease in agricultural areas indicates a shift in agriculture practice, which lately has been the preferred occupation of the residents. Further, the decrease in protected areas indicates the persistent encroachments and abeyance of legislation. In order to address the decreasing agricultural areas, it is crucial to promote sustainable farming practices and increase agricultural productivity to address the escalating requirements of sustenance. This can be accomplished through the implementation of innovative techniques, support for small-scale farmers, and ensuring food security for all, thereby working towards achieving Zero Hunger (SDG-2).

Conclusions

The study applied ANN-based CA approach for prediction of land cover classes which showed substantial agreement between the simulated and the actual LULC map, with the accuracy metric kappa showing a value of 0.77. The model incorporated six driving factors, out of which four were socio-economic spatial parameters, distance from built-up areas, roads, center of town, and streams; while two were geospatial parameters, elevation, and slope. These criteria combinations performed the best in the CA-ANN model showing the highest value of accuracy of 86.83%.

The selection of these factors was based on their potential influence on the study’s outcomes. For instance, proximity to built-up areas may impact pollution levels and development rates, while distance from roads may correlate with traffic noise and urbanization patterns. Elevation and slope could affect water resource accessibility, and proximity to streams might indicate water source quality.

The study predicts that the built-up areas will increase by 17.84% in the year 2025 and 19.69% by the year 2040. The protected areas will decrease by 14.75% and 16.66%, agricultural areas by 2.81% and 2.72%, and barren land by 0.29% and 0.31% for the years 2025 and 2040, respectively.

The rapid increase in population and tourism has led to a significant rise in built-up areas, creating an urgent demand for more land and putting undue pressure on protected areas and agricultural areas. Strict implementation of legislation is necessary to prevent further encroachments in the protected areas. Studying the critical land-use classes in terms of socio-ecological and environmental concerns is valuable for balancing environmental pressures and conservation interventions. The findings can offer guidance to administrators, policymakers, agricultural practitioners, and urban planners in formulating methodologies for sustainable land-use planning and management, fostering the optimal utilization of natural resources.

Availability of data and materials

The data used in the study was downloaded from USGS ( https://earthexplorer.usgs.gov/ ) and is available openly. It is further declared that the data related to the study will be shared upon request.

It is further certified that the research complies with ethical standards, there was no funding for this research, and there are no potential conflicts of interest (financial or non-financial).

Abbreviations

Land use land cover

Cellular automata

Artificial neural network

Multi-layer perceptron

Operational Land Imager

Thermal infrared sensor

Protected areas

Agricultural areas

Built-up areas

Barren land

Water bodies

Maximum likelihood classifier

Modules for land use change

Sustainable Development Goal

Gaigbe-Togbe V, Bassarsky L, Gu D, Spoorenberg T, Zeifman L (2022) World population prospects, Department of Economic and Social Affairs, Population Division: New York, NY, USA

Hertog S, Gerland P, Wilmoth J (2023) India overtakes China as the world’s most populous country. Department of Economic and Social Affairs, United Nations. Policy Brief No. 153

Jat MK, Garg PK, Khare D (2008) Monitoring and modelling of urban sprawl using remote sensing and GIS techniques. Int J Appl Earth Obs Geoinf 10(1):26–43

Google Scholar  

Mondal I, Thakur S, Ghosh P, De TK, Bandyopadhyay J (2019) Land use/land cover modeling of Sagar Island, India using remote sensing and GIS techniques. In Emerging Technologies in Data Mining and Information Security: Proceedings of IEMIS 2018:771–785

Mushtaq F, Pandey AC (2014) Assessment of land use/land cover dynamics vis-à-vis hydrometeorological variability in Wular Lake environs Kashmir Valley, India using multitemporal satellite data. Arab J Geosci 7:4707–4715

Chowdhury M, Hasan ME, Abdullah-Al-Mamun MM (2020) Land use/land cover change assessment of Halda watershed using remote sensing and GIS. Egypt J Remote Sens Sp Sci 23(1):63–75

Rawat JS, Kumar M (2015) Monitoring land use/cover change using remote sensing and GIS techniques: a case study of Hawalbagh block, district Almora, Uttarakhand, India. Egypt J Remote Sens Sp Sci 18(1):77–84

Aithal BH, Ramachandra TV (2016) Visualization of urban growth pattern in Chennai using geoinformatics and spatial metrics. J Indian Soc Remote Sens 44:617–633

Article   Google Scholar  

Fazal S (2000) Urban expansion and loss of agricultural land-a GIS based study of Saharanpur City. India Environ Urban 12(2):133–149

Deka J, Tripathi OP, Khan ML, Srivastava VK (2019) Study on land-use and land-cover change dynamics in Eastern Arunachal Pradesh, NE India using remote sensing and GIS. Trop Ecol 60:199–208

Ghosh S, Sen KK, Rana U, Rao KS, Saxena KG (1996) Application of GIS for land-use/land-cover change analysis in a mountainous terrain. J Indian Soc Remote Sens 24:193–202

Bisht BS, Kothyari BP (2001) Land-cover change analysis of Garur Ganga watershed using GIS/remote sensing technique. J Indian Soc Remote Sens 29:137–141

Berberoglu S, Akin A (2009) Assessing different remote sensing techniques to detect land use/cover changes in the eastern Mediterranean. Int J Appl Earth Obs Geoinf 11(1):46–53

Hegazy IR, Kaloop MR (2015) Monitoring urban growth and land use change detection with GIS and remote sensing techniques in Daqahlia governorate Egypt. Int J Sustain Built Environ 4(1):117–124

Liping C, Yujun S, Saeed S (2018) Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—a case study of a hilly area, Jiangle. China. PLoS One 13(7):e0200493

Article   PubMed   Google Scholar  

Meshesha TW, Tripathi SK, Khare D (2016) Analyses of land use and land cover change dynamics using GIS and remote sensing during 1984 and 2015 in the Beressa Watershed Northern Central Highland of Ethiopia. Model Earth Syst Environ 2:1–12

Mathew A, Chaudhary R, Gupta N, Khandelwal S, Kaul N (2015) Study of urban heat island effect on Ahmedabad City and its relationship with urbanization and vegetation parameters. Int J Comput Math Sci 4:126–135

Muhammad R, Zhang W, Abbas Z, Guo F, Gwiazdzinski L (2022) Spatiotemporal change analysis and prediction of future land use and land cover changes using QGIS MOLUSCE Plugin and Remote Sensing Big Data: a case study of Linyi. China. Land 11(3):419

Zhao S, Liu S, Zhou D (2016) Prevalent vegetation growth enhancement in urban environment. Proc Natl Acad Sci USA 113(22):6313–6318

Article   CAS   PubMed   PubMed Central   ADS   Google Scholar  

Saha AK, Arora MK, Csaplovics E, Gupta RP (2005) Land cover classification using IRS LISS III image and DEM in a rugged terrain: a case study in Himalayas. Geocarto Int 20(2):33–40

Article   ADS   Google Scholar  

Wang SW, Gebru BM, Lamchin M, Kayastha RB, Lee WK (2020) Land use and land cover change detection and prediction in the Kathmandu district of Nepal using remote sensing and GIS. Sustainability 12(9):3925

Gharaibeh A, Shaamala A, Obeidat R, Al-Kofahi S (2020) Improving land-use change modeling by integrating ANN with cellular automata-Markov chain model. Heliyon 6(9):e05092

Article   PubMed   PubMed Central   Google Scholar  

Bhattacharya RK, Das Chatterjee N, Das K (2021) Land use and land cover change and its resultant erosion susceptible level: an appraisal using RUSLE and logistic regression in a tropical plateau basin of West Bengal. India Environ Dev Sustain 23(2):1411–1446

Nagendra H, Munroe DK, Southworth J (2004) From pattern to process: landscape fragmentation and the analysis of land use/land cover change. Agric Ecosyst Environ. 101:111–115

Thakkar AK, Desai VR, Patel A, Potdar MB (2017) Post-classification corrections in improving the classification of land use/land cover of arid region using RS and GIS: the case of Arjuni watershed, Gujarat, India. Egypt J Remote Sens Sp Sci 20(1):79–89

Aburas MM, Ho YM, Ramli MF, Ash’aari ZH, (2016) The simulation and prediction of spatio-temporal urban growth trends using cellular automata models: a review. Int J Appl Earth Obs Geoinf 52:380–389

Tong X, Feng Y (2020) A review of assessment methods for cellular automata models of land-use change and urban growth. Int J Geogr Inf Sci 34(5):866–898

Al-doski J, Mansor SB, Zulhaidi H, Shafri M (2013) Image classification in remote sensing. Int J Sens Netw 3(10):141–148

Bruzzone L, Serpico SB (1997) Classification of imbalanced remote-sensing data by neural networks. Pattern Recognit Lett 18(11–13):1323–1328

Buğday E, Erkan Buğday S (2019) Modeling and simulating land use/cover change using artificial neural network from remotely sensing data. Cerne 25(2):246–254

Kafy AA, Shuvo RM, Naim MN, Sikdar MS, Chowdhury RR, Islam MA, Sarker MH, Khan MH, Kona MA (2021) Remote sensing approach to simulate the land use/land cover and seasonal land surface temperature change using machine learning algorithms in a fastest-growing megacity of Bangladesh. Remote Sens Appl Soc Environ 21:100463

Wolfram S (1984) Cellular automata as models of complexity. Nature 311(5985):419–424

Batty M, Xie Y (1994) Research article modelling inside GIS: part 1. Model structures, exploratory spatial data analysis and aggregation. Int J Geogr Inf Syst 8(3):291–307

Batty M, Xie Y, Sun Z (1999) Modeling urban dynamics through GIS-based cellular automata. Comput Environ Urban Syst 23(3):205–233

Santé I, García AM, Miranda D, Crecente R (2010) Cellular automata models for the simulation of real-world urban processes: a review and analysis. Landsc Urban Plan 96(2):108–122

Sarkar P (2000) A brief history of cellular automata. ACM Comput Surv 32(1):80–107

Leao S, Bishop I, Evans D (2004) Simulating urban growth in a developing nation’s region using a cellular automata-based model. J Urban Plan Dev 130(3):145–158

Lagarias A (2012) Urban sprawl simulation linking macro-scale processes to micro-dynamics through cellular automata, an application in Thessaloniki, Greece. Appl Geogr 34:146–160

Kamaraj M, Rangarajan S (2022) Predicting the future land use and land cover changes for Bhavani basin, Tamil Nadu, India, using QGIS MOLUSCE plugin. Environ Sci Pollut Res 29(57):86337–86348

Atef I, Ahmed W, Abdel-Maguid RH (2023) Future land use land cover changes in El-Fayoum governorate: a simulation study using satellite data and CA-Markov model. Stoch Environ Res Risk Assess 26:1–14

Asori M, Adu P (2023) Modeling the impact of the future state of land use land cover change patterns on land surface temperatures beyond the frontiers of greater Kumasi: a coupled cellular automaton (CA) and Markov chains approaches. Remote Sens Appl Soc Environ 29:100908

Saputra MH, Lee HS (2019) Prediction of land use and land cover changes for North Sumatra, Indonesia, using an artificial-neural-network-based cellular automaton. Sustain 11(11):1–16

Gupta N (2013) Artificial neural network Netw Complex Syst 3(1):24–28

Kadam AK, Wagh VM, Muley AA, Umrikar BN, Sankhua RN (2019) Prediction of water quality index using artificial neural network and multiple linear regression modelling approach in Shivganga River basin, India. Model Earth Syst Environ 5:951–962

Wu X, Liu X, Zhang D, Zhang J, He J, Xu X (2022) Simulating mixed land-use change under multi-label concept by integrating a convolutional neural network and cellular automata: a case study of Huizhou. China GIsci Remote Sens 59(1):609–632

Shafizadeh-Moghadam H, Tayyebi A, Helbich M (2017) Transition index maps for urban growth simulation: application of artificial neural networks, weight of evidence and fuzzy multi-criteria evaluation. Environ Monit Assess 189:1–4

Tayyebi A, Pijanowski BC (2014) Modeling multiple land use changes using ANN, CART and MARS: comparing tradeoffs in goodness of fit and explanatory power of data mining tools. Int J Appl Earth Obs Geoinf 28:102–116

Atkinson PM, Tatnall AR (1997) Introduction neural networks in remote sensing. Int J Remote Sens 18(4):699–709

Hakim AM, Baja S, Rampisela DA, Arif S (2019) Spatial dynamic prediction of landuse/landcover change (case study: Tamalanrea sub-district, Makassar city). IOP Conf Ser Earth Environ Sci 280(1):012023

Mzava P, Nobert J, Valimba P (2019) Land cover change detection in the urban catchments of Dar es Salaam, Tanzania using remote sensing and GIS techniques. Tanz J Sci 45(3):315–329

Gupta V, Ram BK, Kumar S, Sain K (2022) A case study of the 12 July 2021 Bhagsunath (McLeod Ganj) flash flood in Dharamshala, Himachal Pradesh: A warning against constricting natural drainage. J Geol Soc India 98(5):607–610

Weng Q, Fu P (2014) Modeling annual parameters of clear-sky land surface temperature variations and evaluating the impact of cloud cover using time series of Landsat TIR data. Remote Sens Environ 140:267–278

Mishra PK, Rai A, Rai SC (2020) Land use and land cover change detection using geospatial techniques in the Sikkim Himalaya, India. Egypt J Remote Sens Sp Sci 23(2):133–143

Phinzi K, Ngetar NS, Pham QB, Chakilu GG, Szabó S (2023) Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest. Earth Sci Inform 16(4):3667–3677

Gebreslasie MT, Ahmed FB, Van Aardt JA, Blakeway F (2011) Individual tree detection based on variable and fixed window size local maxima filtering applied to IKONOS imagery for even-aged Eucalyptus plantation forests. Int J Remote Sens 32(15):4141–4154

Kumar D (2017) Monitoring and assessment of land use and land cover changes (1977–2010) in Kamrup District of Assam, India using remote sensing and GIS techniques. Appl Ecol Environ Res 15(3):221–239

Article   MathSciNet   Google Scholar  

Zaz SN, Romshoo SA (2012) Assessing the geoindicators of land degradation in the Kashmir Himalayan region, India. Nat Hazards 64:1219–1245

Deng Z, Zhang X, Li D, Pan G (2015) Simulation of land use/land cover change and its effects on the hydrological characteristics of the upper reaches of the Hanjiang Basin. Environ Earth Sci 73:1119–1132

Yeh AG, Li X (1998) Sustainable land development model for rapid growth areas using GIS. Int J Geogr Inf Sci 12(2):169–189

Martins VS, Kaleita AL, Gelder BK, da Silveira HL, Abe CA (2020) Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution. ISPRS J Photogramm Remote Sens 168:56–73

Chettry V, Surawar M (2021) Delineating urban growth boundary using remote sensing, ANN-MLP and CA model: a case study of Thiruvananthapuram urban agglomeration. India J Indian Soc Remote Sens 49(10):2437–2450

Bozkaya AG, Balcik FB, Goksel C, Esbah H (2015) Forecasting land-cover growth using remotely sensed data: a case study of the Igneada protection area in Turkey. Environ Monit Assess 187:1–8

Feng Y (2017) Modeling dynamic urban land-use change with geographical cellular automata and generalized pattern search-optimized rules. Int J Geogr Inf Sci 31(6):1198–1219

Lillesand T, Kiefer RW, Chipman J (2015) Remote sensing and image interpretation. John Wiley & Sons

Van Vliet J, Bregt AK, Hagen-Zanker A (2011) Revisiting kappa to account for change in the accuracy assessment of land-use change models. Ecol Modell 222(8):1367–1375

Rwanga SS, Ndambuki JM (2017) Accuracy assessment of land use/land cover classification using remote sensing and GIS. Int J Geosci 8(04):611

Download references

Acknowledgements

Not applicable.

The authors, Nishant Mehra and Dr. Janaki Ballav Swain, hereby certify that no funding was received.

Author information

Authors and affiliations.

School of Civil Engineering, Lovely Professional University, Punjab, 144001, India

Nishant Mehra & Janaki Ballav Swain

You can also search for this author in PubMed   Google Scholar

Contributions

It is certified that both the authors had contributed equally in the preparation of the manuscript. It is also certified that all authors have read and approved the manuscript.

Corresponding author

Correspondence to Nishant Mehra .

Ethics declarations

Competing interests.

The authors, Nishant Mehra and Dr. Janaki Ballav Swain, hereby certify that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Mehra, N., Swain, J.B. Assessment of land use land cover change and its effects using artificial neural network-based cellular automation. J. Eng. Appl. Sci. 71 , 70 (2024). https://doi.org/10.1186/s44147-024-00402-0

Download citation

Received : 03 November 2023

Accepted : 27 February 2024

Published : 14 March 2024

DOI : https://doi.org/10.1186/s44147-024-00402-0

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial neural network (ANN)
• Supervised classification
• Cellular automata (CA)
• Land use land cover (LULC)

Carbon emission of regional land use and its decomposition analysis: Case study of Nanjing City, China

• Published: 12 September 2014
• Volume 25 , pages 198–212, ( 2015 )

Cite this article

• Rongqin Zhao 1 , 2 ,
• Xianjin Huang 2 ,
• Ying Liu 3 ,
• Taiyang Zhong 2 ,
• Minglei Ding 1 &
• Xiaowei Chuai 2  

695 Accesses

50 Citations

Explore all metrics

Through the matching relationship between land use types and carbon emission items, this paper estimated carbon emissions of different land use types in Nanjing City, China and analyzed the influencing factors of carbon emissions by Logarithmic Mean Divisia Index (LMDI) model. The main conclusions are as follows: 1) Total anthropogenic carbon emission of Nanjing increased from 1.22928 × 10 7 t in 2000 to 3.06939 × 10 7 t in 2009, in which the carbon emission of Inhabitation, mining & manufacturing land accounted for 93% of the total. 2) The average land use carbon emission intensity of Nanjing in 2009 was 46.63 t/ha, in which carbon emission intensity of Inhabitation, mining & manufacturing land was the highest (200.52 t/ha), which was much higher than that of other land use types. 3) The average carbon source intensity in Nanjing was 16 times of the average carbon sink intensity (2.83 t/ha) in 2009, indicating that Nanjing was confronted with serious carbon deficit and huge carbon cycle pressure. 4) Land use area per unit GDP was an inhibitory factor for the increase of carbon emissions, while the other factors were all contributing factors. 5) Carbon emission effect evaluation should be introduced into land use activities to formulate low-carbon land use strategies in regional development.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Strategies for mitigation of climate change: a review

Enhancing Carbon Sequestration through Afforestation: Evaluating the Impact of Land Use and Cover Changes on Carbon Storage Dynamics

Deforestation and Forests Degradation Impacts on the Environment

Ali G, Nitivattananon V, 2012. Exercising multidisciplinary approach to assess interrelationship between energy use, carbon emission and land use change in a metropolitan city of Pakistan. Renewable and Sustainable Energy Reviews , 16(1): 775–786. doi: 10.1016/j.bbr.2011.03.031

Article   Google Scholar  

Ang B W, 2004. Decomposition analysis for policymaking in energy: Which is the preferred methods? Energy Policy , 32(9): 1131–1139. doi: 10.1016/S0301-4215(03)00076-4

Araujo M S M, Silva C, Campos C P, 2009. Land use change sector contribution to the carbon historical emissions and the sustainability—Case study of the Brazilian Legal Amazon. Renewable and Sustainable Energy Reviews , 13(3): 696–702. doi: 10.1016/j.rser.2007.10.008

Cai Bofeng, Liu Chunlan, Chen Caocao, 2009. City’s Greenhouse Gas Emission Inventory Research . Beijing: Chemical Industry Press. (in Chinese)

Google Scholar  

Christen A, Coops N, Kellett R et al. , 2010. A LiDAR-based Urban Metabolism Approach to Neighborhood Scale Energy and Carbon Emissions Modeling . University of British Columbia.

Churkina G, 2008. Modeling the carbon cycle of urban systems. Ecological Modeling , 216(2): 107–113. doi: 10.1016/j.ecolmodel.2008.03.006

DeFries R S, Field C B, Fung I et al. , 1999. Combining satellite data and biogeochemical models to estimate global effects of human-induced land cover change on carbon emissions and primary productivity. Global Biogeochemical Cycle , 13(3): 803–815. doi: 10.1029/1999GB900037

Duan Xiaonan, Wang Xiaoke, Lu Fei et al. , 2008. Carbon sequestration and its potential by wetland ecosystems in China. Acta Ecologica Sinica , 28(2): 463–469. (in Chinese)

Fang J Y, Chen A P, Peng C H et al. , 2001. Changes in forest biomass carbon storage in China between 1949 and 1998. Science , 292(5525): 2320–2322. doi: 10.1126/science.1058629

Fang Jingyun, Guo Zhaodi, Piao Shilong et al. , 2007. Estimation on terrestrial vegetation carbon sinks in China from 1981 to 2000. Science in China ( Series D ), 37(6): 804–812. (in Chinese)

Fang Jingyun, Liu Guohua, Xu Songling, 1996. Carbon cycle of terrestrial ecosystem in China and its global meaning. In: Wang Gengchen et al . (eds). The Measurement of Greenhouse Gases and Their Release and Related Processes . Beijing: China Environment Science Press, 129–139. (in Chinese)

Ge Quansheng, Dai Junhu, He Fanneng et al. , 2008. Research on land use/land cover change and carbon cycle in the past 300 years in China. Science in China ( Series D ), 38(2): 197–210. (in Chinese)

Guan Dongsheng, Chen Yujuan, Huang Fenfang, 1998. The storage and distribution of carbon in urban vegetation and its roles in balance and oxygen in Guangzhou. China Environmental Science,18(5): 437–441. (in Chinese)

Guo Yungong, 2009. The Analysis on Calculation and Characteristics of Greenhouse Gas Emission in Mega-cities . Shanghai: East China Normal University. (in Chinese)

Houghton R A, 1999. The annual net flux of carbon to the atmosphere from changes in land use 1850–1990. Tellus Series B-Chemical and Physical Meteorology , 51(2): 298–313. doi: 10.1034/j.1600-0889.1999.00013.x

Houghton R A, Hackler J L, 2003. Sources and sinks of carbon from land-use change in China. Global Biogeochemical Cycles , 17(2): 1034–1047. doi: 10.1029/2002GB001970

Houghton R A, Hackler J L, Lawrence K T, 1999. The U.S. Carbon Budget: Contributions from land-use change. Science , 285(5427): 574–578. doi: 10.1126/science.285.5427.574

IPCC (Intergovernmental Panel on Climate Change), 2006. 2006 IPCC Guidelines for National Greenhouse Gas Inventories.

Kalnay E, Cai M, 2003. Impact of urbanization and land-use change on climate. Nature , 423: 528–531.

Koemer B, Klopatek J, 2002. Anthropogenic and natural CO 2 emission sources in an arid urban environment. Environmental Pollution , 116(S1): S45–S51. doi: 10.1016/S0269-7491(01)00246-9

Kuang Yaoqiu, Ouyang Tingping, Zou Yi et al. , 2010. Present situation of carbon source and sink and potential for increase of carbon sink in Guangdong Province. China Population Resources and Environment , 20(S): 154–158. (in Chinese)

Kwon H Y, Mueller S, Dunn J B et al. , 2013. Modeling state-level soil carbon emission factors under various scenarios for direct land use change associated with United States biofuel feedstock production. Biomass and Bioenergy , 55: 299–310. doi: 10.1016/j.biombioe.2013.02.021

Lai Li, Huang Xianjin, 2011. Carbon Emission Effect of Land Use in China . Nanjing: Nanjing University Press. (in Chinese)

Li Kerang, 2000. Land Use Change , Net Emission of Greenhouse Gases and the Carbon Cycle in Terrestrial Ecosystems . Beijing: China Meteorological Press, 260. (in Chinese)

Liu Hongguang, Liu Weidong, 2009. Decomposition of energy-induced CO 2 emissions in industry of China. Progress in Geography , 28(2): 285–292. (in Chinese)

Liu L C, Fan Y, Wu G et al. , 2007. Using LMDI method to analyze the change of China’s industrial CO 2 emissions from final fuel use: An empirical analysis. Energy Policy , 35(11): 5892–5900. doi: 10.1016/j.enpol.2007.07.010

Ma C B, Stern D I, 2008. Biomass and China’s carbon emissions: A missing piece of carbon decomposition. Energy Policy , 36(7): 2517–2526. doi: 10.1016/j.enpol.2008.03.013

Malla S, 2009. CO 2 emissions from electricity generation in seven Asia-Pacific and North American countries: A decomposition analysis. Energy Policy , 37(1): 1–9. doi: 10.1016/j.enpol.2008.08.010

McGuire A D, Sitch S, Clein J S et al. , 2001. Carbon balance of the terrestrial biosphere in the twentieth century: Analyses of CO 2 , climate and land use effects with four process-based ecosystem models. Global Biogeochemical Cycle , 15(1): 183–206. doi: 10.1029/2000GB001298

Ministry of Housing and Urban-rural Development of China, 2010. China Urban Construction Statistical Yearbook . Beijing: China Planning Press. (in Chinese)

Nanjing Statistical Bureau, 2010a. Statistical Yearbook of Nanjing City . Nanjing: Nanjing Press. (in Chinese)

Nanjing Statistical Bureau, 2010b. General Economic Surveying Yearbook of Nanjing . Nanjing: Nanjing Press. (in Chinese)

National Bureau of Statistics of China, 2008. China Energy Statistical Yearbook . Beijing: China Statistics Press. (in Chinese)

Quay P D, Tilbrook B, Wong C S, 1992. Oceanic uptake of fossil fuel CO 2 : Carbon-13 evidence. Science , 256(5053): 74–79. doi: 10.1126/science.256.5053.74

Schindler D W, 1999. Carbon cycling: The mysterious missing sink. Nature , 398: 105–107. doi: 10.1038/18111

Shao C F, Guan Y, Wan Z et al. , 2014. Performance and decomposition analyses of carbon emissions from industrial energy consumption in Tianjin, China. Journal of Cleaner Production , 64: 590–601. doi: 10.1016/j.jclepro.2013.08.017

Soytasa U, Sari R, Ewing B T, 2007. Energy consumption, income, and carbon emissions in the United States. Ecological Economics , 62(3–4): 482–489. doi: 10.1016/j.ecolecon.2006.07.009

Statistical Bureau of Jiangsu Province, 2010. Statistical Yearbook of Jiangsu Province . Beijing: China Statistics Press. (in Chinese)

Svirejeva-Hopkins A, Schellnhuber H J, 2006. Modelling carbon dynamics from urban land conversion: fundamental model of city in relation to a local carbon cycle. Carbon Balance and Management , 1: 1–8. doi: 10.1186/1750-0680-1-8

Svirejeva-Hopkins A, Schellnhuber H J, 2008. Urban expansion and its contribution to the regional carbon emissions: Using the model based on the population density distribution. Ecological Modelling , 216(2): 208–216. doi: 10.1016/j.ecolmodel.2008.03.023

Tang Hongxia, Han Dan, Zhao Youcai, 2009. Greenhouse Gases Emission Reduction and Controlling Technology of Agriculture and Forestry . Beijing: Chemical Industry Press, 87–99. (in Chinese)

Tian X, Chang M, Shi F et al. , 2012. Structural decomposition analysis of the carbonization process in Beijing: A regional explanation of rapid increasing carbon dioxide emission in China. Energy Policy , 53: 279–286. doi: 10.1016/j.enpol.2012.10.054

Tunc G I, Turut-Asik S, Akbostanci E, 2009. A decomposition analysis of CO 2 emissions from energy use: Turkish case. Energy Policy , 37(11): 4689–4699. doi: 10.1016/j.enpol.2009.06.019

Xie Hongyu, Chen Xiansheng, Lin Kairong, 2008 The ecological footprint analysis of fossil energy and electricity. Acta Ecologica Sinica , 28(4):1729–1735. (in Chinese)

Xu Guoquan, Liu Zeyuan, Jiang Zhaohua, 2006. Decomposition model and empirical study of carbon emissions for China, 1995–2004. China Population Resources and Environment , 16(6): 158–161. (in Chinese)

Ye Duzheng, Chen Panqin, 1992. Study on Prediction of Global Change in China ( the second part ). Beijing: Earthquake Press. (in Chinese)

Zhang C, Tian H Q, Chen G S et al. , 2012. Impacts of urbanization on carbon balance in terrestrial ecosystems of the Southern United States. Environmental Pollution , 164: 89–101. doi: 10.1016/j.envpol.2012.01.020

Zhao M, Tan L R, Zhang W G et al. , 2010. Decomposing the influencing factors of industrial carbon emissions in Shanghai using the LMDI method. Energy ? 35(6): 2505–2510. doi: 10.1016/j.energy.2010.02.049

Zhao R Q, Huang X J, Zhong T Y et al. , 2011. Carbon footprint of different industrial spaces based on energy consumption in China. Journal of Geographical Sciences , 21(2): 285–300. doi: 10.1007/s11442-011-0845-6

Download references

Author information

Authors and affiliations.

School of Resources and Environment, North China University of Water Resources and Electric Power, Zhengzhou, 450045, China

Rongqin Zhao & Minglei Ding

School of Geographic and Oceanographic Sciences, Nanjing University, Nanjing, 210093, China

Rongqin Zhao, Xianjin Huang, Taiyang Zhong & Xiaowei Chuai

College of Civil Construction Engineering, Zhengzhou Institute of Aeronautical Industry Management, Zhengzhou, 450046, China

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Rongqin Zhao .

Additional information

Foundation item: Under the auspices of National Natural Science Foundation of China (No. 41301633), National Social Science Foundation of China (No. 10ZD&030), Postdoctoral Science Foundation of China (No. 2012M511243, 2013T60518), Clean Development Mechanism Foundation of China (No. 1214073, 2012065)

Rights and permissions

Reprints and permissions

About this article

Zhao, R., Huang, X., Liu, Y. et al. Carbon emission of regional land use and its decomposition analysis: Case study of Nanjing City, China. Chin. Geogr. Sci. 25 , 198–212 (2015). https://doi.org/10.1007/s11769-014-0714-1

Download citation

Received : 06 January 2014

Accepted : 21 April 2014

Published : 12 September 2014

Issue Date : April 2015

DOI : https://doi.org/10.1007/s11769-014-0714-1

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• carbon emission
• Logarithmic Mean Divisia Index (LMDI) model
• decomposition analysis
• Nanjing City
• Find a journal
• Publish with us
• Track your research

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

A computational geospatial approach to assessing land-use compatibility in urban planning.

1. Introduction

2. literature review, 2.1. theoretical background, 2.2. land-use assessment, 3. methods and data, 3.1. case study, 3.2. methodology, 3.2.1. overview, 3.2.2. defining compatibility values, 3.2.3. spatial analysis of neighborhood effects, 3.2.4. computation of cell values.

• The variable “m” represents the distance from the central cell to the edge of the neighboring radius in the x -axis, which is calculated as (x − 1)/2.
• The variable “n” represents the distance from the central cell to the edge of the neighboring radius in the y -axis, calculated as (y − 1)/2.
• “W N ” denotes the weight assigned to each cell within the neighborhood, which depends on its distance from the cell under study.
• “C” represents the compatibility level corresponding to the specific land-use category of the cell under study.
• “Cp” denotes the points acquired by the cell under study based on the compatibility level.

3.2.5. Implementation in GIS

4. findings.

• The effect radii for industrial and non-urban uses were systematically varied from 100 to 500 m in 100 m intervals to assess the impacts on proximal residential area compatibility. As the radii were increased, more residential areas shifted from completely compatible to relatively or completely incompatible in the model outputs, affirming the technique’s ability to realistically capture extended impact zones.
• The model outputs were compared with observed land-use conflicts reported by residents and planning authorities through surveys and public forums. Approximately 84% of the identified and reported conflicts occurred in areas categorized as relatively or completely incompatible by the model, suggesting strong validity in the model’s categorization.
• Sensitivity analysis was undertaken by varying the cell size resolution from 1 to 10 m. While some minor variations occurred with smaller cell sizes below 5 m, the overall compatibility patterns and hotspots remained consistent, demonstrating the robustness of the model across scales.

5. Discussion

6. conclusions, author contributions, institutional review board statement, informed consent statement, data availability statement, conflicts of interest.

• Michalos, A.C. Encyclopedia of Quality of Life and Well-Being Research ; Springer: Dordrecht, The Netherlands, 2014; Volume 171. [ Google Scholar ]
• Samat, N.; Mahamud, M.A.; Tan, M.L.; Maghsoodi Tilaki, M.J.; Tew, Y.L. Modelling land cover changes in peri-urban areas: A case study of george town conurbation, Malaysia. Land 2020 , 9 , 373. [ Google Scholar ] [ CrossRef ]
• Kılkış, Ş. Urban emissions and land use efficiency scenarios towards effective climate mitigation in urban systems. Renew. Sustain. Energy Rev. 2022 , 167 , 112733. [ Google Scholar ] [ CrossRef ]
• Zheng, H.; Wu, Y.; He, H.; Delang, C.O.; Qian, J.; Lu, J.; Yao, Z.; Li, G. Urban land use eco-efficiency and improvement in the western region of China. J. Clean. Prod. 2023 , 412 , 137385. [ Google Scholar ] [ CrossRef ]
• Rahman, M.M.; Szabó, G. Multi-objective urban land use optimization using spatial data: A systematic review. Sustain. Cities Soc. 2021 , 74 , 103214. [ Google Scholar ] [ CrossRef ]
• Taleshi, M.; Ghobadi, A. Urban land use sustainability assessment through evaluation of compatibility matrix case study: Karaj City. OIDA Int. J. Sustain. Dev. 2012 , 3 , 57–64. [ Google Scholar ]
• Iannillo, A.; Fasolino, I. Land-use mix and urban sustainability: Benefits and indicators analysis. Sustainability 2021 , 13 , 13460. [ Google Scholar ] [ CrossRef ]
• Fu, X.-L.; Zhou, J.; Tang, W.-W.; Liu, Y.; Li, Z.-L.; Li, P.; Chen, J. Study on the compatibility effect and active constituents of atractylodis rhizoma in ermiao wan against acute gouty arthritis. J. Ethnopharmacol. 2021 , 279 , 114353. [ Google Scholar ] [ CrossRef ]
• Freestone, R.; Favaro, P. The social sustainability of smart cities: A conceptual framework. City Cult. Soc. 2022 , 29 , 100460. [ Google Scholar ]
• Huang, G.; Li, D.; Zhu, X.; Zhu, J. Influencing factors and their influencing mechanisms on urban resilience in China. Sustain. Cities Soc. 2021 , 74 , 103210. [ Google Scholar ] [ CrossRef ]
• Luan, C.; Liu, R.; Peng, S. Land-use suitability assessment for urban development using a GIS-based soft computing approach: A case study of Ili Valley, China. Ecol. Indic. 2021 , 123 , 107333. [ Google Scholar ] [ CrossRef ]
• Hersperger, A.M.; Oliveira, E.; Pagliarin, S.; Palka, G.; Verburg, P.; Bolliger, J.; Grădinaru, S. Urban land-use change: The role of strategic spatial planning. Glob. Environ. Change 2018 , 51 , 32–42. [ Google Scholar ] [ CrossRef ]
• Manzello, S.L. Encyclopedia of Wildfires and Wildland-Urban Interface (WUI) Fires ; Springer: Berlin/Heidelberg, Germany, 2020. [ Google Scholar ]
• Zhuo, Y.; Zheng, H.; Wu, C.; Xu, Z.; Li, G.; Yu, Z. Compatibility mix degree index: A novel measure to characterize urban land use mix pattern. Comput. Environ. Urban Syst. 2019 , 75 , 49–60. [ Google Scholar ] [ CrossRef ]
• Siegel, K.; Farah Perez, A.; Kinnebrew, E.; Mills-Novoa, M.; Ochoa, J.; Shoffner, E. Integration of qualitative and quantitative methods for land-use-change modeling in a deforestation frontier. Conserv. Biol. 2022 , 36 , e13924. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Koroso, N.H.; Zevenbergen, J.A.; Lengoiboni, M. Urban land use efficiency in Ethiopia: An assessment of urban land use sustainability in Addis Ababa. Land Use Policy 2020 , 99 , 105081. [ Google Scholar ] [ CrossRef ]
• Shen, X.; Wang, X.; Zhang, Z.; Lu, Z.; Lv, T. Evaluating the effectiveness of land use plans in containing urban expansion: An integrated view. Land Use Policy 2019 , 80 , 205–213. [ Google Scholar ] [ CrossRef ]
• Yang, J.; Yang, Y.; Tang, W. Development of evaluation model for intensive land use in urban centers. Front. Archit. Res. 2012 , 1 , 405–410. [ Google Scholar ] [ CrossRef ]
• Li, Y.; Zhang, S. Urban Land Use Analysis. In Applied Research Methods in Urban and Regional Planning ; Springer: Berlin/Heidelberg, Germany, 2022; pp. 269–288. [ Google Scholar ]
• Ahadnejad Reveshty, M.; Tahmasebi Moghaddam, H.; Shami, F.; Moharrami, S. Spatial explanation of urban sprawl phenomenon (Case study: Qaemshahr city). J. Urban Soc. Geogr. 2019 , 6 , 1–13. [ Google Scholar ]
• Lagopoulos, A.P. Clarifying theoretical and applied land-use planning concepts. Urban Sci. 2018 , 2 , 17. [ Google Scholar ] [ CrossRef ]
• Rounsevell, M.D.; Pedroli, B.; Erb, K.-H.; Gramberger, M.; Busck, A.G.; Haberl, H.; Kristensen, S.; Kuemmerle, T.; Lavorel, S.; Lindner, M. Challenges for land system science. Land Use Policy 2012 , 29 , 899–910. [ Google Scholar ] [ CrossRef ]
• Filatova, T. Empirical agent-based land market: Integrating adaptive economic behavior in urban land-use models. Comput. Environ. Urban Syst. 2015 , 54 , 397–413. [ Google Scholar ] [ CrossRef ]
• Liang, H.; Liu, W.; Liu, H.; Ling, Y.; Liu, Y. Coupling relationship between socio-economy benefits and eco-environment benefits of land use in Shenzhen City. Sci. Geogr. Sin. 2008 , 28 , 636–641. [ Google Scholar ]
• Nakamura, H. Relationship among land price, entrepreneurship, the environment, economics, and social factors in the value assessment of Japanese cities. J. Clean. Prod. 2019 , 217 , 144–152. [ Google Scholar ] [ CrossRef ]
• Karakayacı, Z. Regression analysis for the factor affecting on farm land/urban land value in urban sprawl. Turk. J. Agric.—Food Sci. Technol. 2018 , 6 , 1357–1361. [ Google Scholar ] [ CrossRef ]
• Schüle, S.A.; Gabriel, K.M.; Bolte, G. Relationship between neighbourhood socioeconomic position and neighbourhood public green space availability: An environmental inequality analysis in a large German city applying generalized linear models. Int. J. Hyg. Environ. Health 2017 , 220 , 711–718. [ Google Scholar ] [ CrossRef ]
• Chisholm, M. Location and Land Use: Toward a General Theory of Land Rent ; JSTOR: New York, NY, USA, 1966. [ Google Scholar ]
• Clapp, J.M. Urban land use succession under risk. Urban Stud. 1977 , 14 , 73–77. [ Google Scholar ] [ CrossRef ]
• Lee, Y. A conceptual discussion and an empirical analysis of commercial land-use succession. Environ. Plan. A 1974 , 6 , 655–674. [ Google Scholar ] [ CrossRef ]
• Smith, P.J.; McCann, L.D. Residential land use change in inner Edmonton. Ann. Assoc. Am. Geogr. 1981 , 71 , 536–551. [ Google Scholar ] [ CrossRef ]
• Liu, F. Environmental Justice Analysis: Theories, Methods, and Practice ; CRC Press: Boca Raton, FL, USA, 2001. [ Google Scholar ]
• Gao, P.; Li, Y.; Gong, J.; Huang, G. Urban land-use planning under multi-uncertainty and multiobjective considering ecosystem service value and economic benefit-A case study of Guangzhou, China. Ecol. Complex. 2021 , 45 , 100886. [ Google Scholar ] [ CrossRef ]
• Verma, P.; Singh, P.; Singh, R.; Raghubanshi, A. Urban Ecology: Emerging Patterns and Social-Ecological Systems ; Elsevier: Amsterdam, The Netherlands, 2020. [ Google Scholar ]
• Fu, Y.; Zhou, T.; Yao, Y.; Qiu, A.; Wei, F.; Liu, J.; Liu, T. Evaluating efficiency and order of urban land use structure: An empirical study of cities in Jiangsu, China. J. Clean. Prod. 2021 , 283 , 124638. [ Google Scholar ] [ CrossRef ]
• Tonne, C.; Adair, L.; Adlakha, D.; Anguelovski, I.; Belesova, K.; Berger, M.; Brelsford, C.; Dadvand, P.; Dimitrova, A.; Giles-Corti, B. Defining pathways to healthy sustainable urban development. Environ. Int. 2021 , 146 , 106236. [ Google Scholar ] [ CrossRef ]
• Taleai, M.; Sharifi, A.; Sliuzas, R.; Mesgari, M. Evaluating the compatibility of multi-functional and intensive urban land uses. Int. J. Appl. Earth Obs. Geoinf. 2007 , 9 , 375–391. [ Google Scholar ] [ CrossRef ]
• Pahlavani, P.; Sheikhian, H.; Bigdeli, B. Evaluation of residential land use compatibilities using a density-based IOWA operator and an ANFIS-based model: A case study of Tehran, Iran. Land Use Policy 2020 , 90 , 104364. [ Google Scholar ] [ CrossRef ]
• Sadiq, F.K.; Ya’u, S.L.; Aliyu, J.; Maniyunda, L.M. Evaluation of land suitability for soybean production using GIS-based multi-criteria approach in Kudan Local Government area of Kaduna State Nigeria. Environ. Sustain. Indic. 2023 , 20 , 100297. [ Google Scholar ] [ CrossRef ]
• Maleki, J.; Hakimpour, F.; Masoumi, Z. A parcel-level model for ranking and allocating urban land-uses. ISPRS Int. J. Geo-Inf. 2017 , 6 , 273. [ Google Scholar ] [ CrossRef ]
• Wang, A.; Wang, H.; Chan, E.H. The incompatibility in urban green space provision: An agent-based comparative study. J. Clean. Prod. 2020 , 253 , 120007. [ Google Scholar ] [ CrossRef ]
• Shi, H.; Zhao, M.; Chi, B. Behind the land use mix: Measuring the functional compatibility in urban and sub-urban areas of China. Land 2021 , 11 , 2. [ Google Scholar ] [ CrossRef ]
• Chakraborty, A.; McMillan, A. GIS and scenario analysis: Tools for better urban planning. In Comprehensive Geographic Information Systems ; Elsevier: Amsterdam, The Netherlands, 2017; pp. 371–380. [ Google Scholar ]
• Cai, G.; Zhang, J.; Du, M.; Li, C.; Peng, S. Identification of urban land use efficiency by indicator-SDG 11.3.1. PLoS ONE 2020 , 15 , e0244318. [ Google Scholar ]
• Brown, G.; Raymond, C.M. Methods for identifying land use conflict potential using participatory mapping. Landsc. Urban Plan. 2014 , 122 , 196–208. [ Google Scholar ] [ CrossRef ]
• De Jong, L.; De Bruin, S.; Knoop, J.; van Vliet, J. Understanding land-use change conflict: A systematic review of case studies. J. Land Use Sci. 2021 , 16 , 223–239. [ Google Scholar ] [ CrossRef ]
• Pourmohammadi, M.R. Urban Land Use Planning ; SAMT Publications: Tehran, Iran, 2003. (In Persian) [ Google Scholar ]
• Wei, R.; Ye, C.; Sui, T.; Ge, Y.; Li, Y.; Li, J. Combining spatial response features and machine learning classifiers for landslide susceptibility mapping. Int. J. Appl. Earth Obs. Geoinf. 2022 , 107 , 102681. [ Google Scholar ] [ CrossRef ]
• Chakir, R.; Le Gallo, J. Spatial Autocorrelation in Econometric Land Use Models: An Overview. In Advances in Contemporary Statistics and Econometrics: Festschrift in Honor of Christine Thomas-Agnan ; Springer: Cham, Switzerland, 2021; pp. 339–362. [ Google Scholar ]
• Overmars, K.d.; De Koning, G.; Veldkamp, A. Spatial autocorrelation in multi-scale land use models. Ecol. Model. 2003 , 164 , 257–270. [ Google Scholar ] [ CrossRef ]
• Li, L.; Tang, H.; Lei, J.; Song, X. Spatial autocorrelation in land use type and ecosystem service value in Hainan Tropical Rain Forest National Park. Ecol. Indic. 2022 , 137 , 108727. [ Google Scholar ] [ CrossRef ]
• Kangas, K.; Brown, G.; Kivinen, M.; Tolvanen, A.; Tuulentie, S.; Karhu, J.; Markovaara-Koivisto, M.; Eilu, P.; Tarvainen, O.; Similä, J. Land use synergies and conflicts identification in the framework of compatibility analyses and spatial assessment of ecological, socio-cultural and economic values. J. Environ. Manag. 2022 , 316 , 115174. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Lozada, A.; Bertin, A. Spatial autocorrelation signatures of ecological determinants on plant community characteristics in high Andean wetlands. Sci. Rep. 2022 , 12 , 13770. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Tang, X.; Li, C.Z.; Jiang, L.; Lai, X.; Zhang, L. A Spatial Autocorrelation Analysis for Land Use Change in the Guangdong-Hong Kong-Macao Greater Bay Area. In Proceedings of the 26th International Symposium on Advancement of Construction Management and Real Estate, Beijing, China, 20–22 November 2021; Springer: Berlin/Heidelberg, Germany, 2021. [ Google Scholar ]
• Wang, Z.; Han, Q.; De Vries, B. Land use spatial optimization using accessibility maps to integrate land use and transport in urban areas. Appl. Spat. Anal. Policy 2022 , 15 , 1193–1217. [ Google Scholar ] [ CrossRef ]
• Yang, Q.; Pu, L.; Jiang, C.; Gong, G.; Tan, H.; Wang, X.; He, G. Unveiling the spatial-temporal variation of urban land use efficiency of Yangtze River Economic Belt in China under carbon emission constraints. Front. Environ. Sci. 2023 , 10 , 1096087. [ Google Scholar ] [ CrossRef ]
• Burghardt, K.; Uhl, J.H.; Lerman, K.; Leyk, S. Road network evolution in the urban and rural United States since 1900. Comput. Environ. Urban Syst. 2022 , 95 , 101803. [ Google Scholar ] [ CrossRef ]
• Sun, S.; Parker, D.C.; Brown, D.G. From an agent-based laboratory to the real world: Effects of “neighborhood” size on urban sprawl. Comput. Environ. Urban Syst. 2023 , 99 , 101889. [ Google Scholar ] [ CrossRef ]

Click here to enlarge figure

Share and Cite

Mansourihanis, O.; Maghsoodi Tilaki, M.J.; Yousefian, S.; Zaroujtaghi, A. A Computational Geospatial Approach to Assessing Land-Use Compatibility in Urban Planning. Land 2023 , 12 , 2083. https://doi.org/10.3390/land12112083

Mansourihanis O, Maghsoodi Tilaki MJ, Yousefian S, Zaroujtaghi A. A Computational Geospatial Approach to Assessing Land-Use Compatibility in Urban Planning. Land . 2023; 12(11):2083. https://doi.org/10.3390/land12112083

Mansourihanis, Omid, Mohammad Javad Maghsoodi Tilaki, Samira Yousefian, and Ayda Zaroujtaghi. 2023. "A Computational Geospatial Approach to Assessing Land-Use Compatibility in Urban Planning" Land 12, no. 11: 2083. https://doi.org/10.3390/land12112083

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

• Skip to main content
• Keyboard shortcuts for audio player

Weekend Edition Sunday

• Latest Show

Sunday Puzzle

• Corrections

Listen to the lead story from this episode.

Politics chat: Trump and Biden's policy agendas will take center stage at the debate

by  Ayesha Rascoe ,  Mara Liasson

Russia is finding new supporters after being isolated by the West

by  Charles Maynes

State laws complicate the federal ban on gun possession for domestic abusers

by  Paige Pfleger ,  Ayesha Rascoe

Middle East

Lebanon is home to the most refugees per capita. now it wants to send some of them back.

by  Jane Arraf

Lebanon is home to the most number of refugees. Now it wants to send some of them back

Jonathan merritt's book reminds kids what makes them different makes them special.

by  Jason DeRose

Republican lawmakers in Connecticut fight against a future ban on gas-powered vehicles

by  Molly Ingram

Sunday Puzzle NPR hide caption

Sunday Puzzle: Summer movie blockbusters

by  Will Shortz

Years before intimacy coordinators on Hollywood sets, there was the 1996 film Bound

by  Isabella Gomez Sarmiento

Music Interviews

Agalisiga mackey reflects on writing songs in his native cherokee language.

by  Ryan Benk ,  Ayesha Rascoe

Tsitsutsa Tsigesv reflects on writing songs in his native Cherokee language

How biden is getting ready for his high-stakes debate with former president trump.

by  Asma Khalid

Young Black voters are feeling increasingly ambivalent about the Democratic Party

by  Ayesha Rascoe

Hungary's far-right leader is set to take over rotating presidency of the EU

If ai provides false information, who takes the blame, the hottest new concert venue could be your local cemetery.

by  Alison Cuddy

Health Care

'medicaid unwinding' can be dangerous for those who need opioid addiction medications.

by  Stephanie Colombini

'Return to Rickwood' traces the history of the Major League's newest field

Author interviews, an incident at a grocery store set sadie dingfelder down the path of writing her book.

Searching for a song you heard between stories? We've retired music buttons on these pages. Learn more here.

Highest and Best Use Analysis...what is it‪?‬ Real Estate Investment Insights

I walk through, at a high level, my Highest & Best Use (HBU) Analysis.  The case study looks at a small retail center with some excess land and how I go about evaluating the property and what might be the best options for the ownership group to consider.  

• Episode Website
• More Episodes
• © 2023 DerekDoke|CCIM