Next Article in Journal
An Improved Method for Estimating Blue Carbon Storage in Coastal Salt Marsh Wetlands: Considering the Heterogeneity of Soil Thickness
Previous Article in Journal
Mapping the Potential to Establish Multifunctional Agrofood Parks to Foster the Food Transition at a Regional Level
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Land
Volume 14
Issue 4
10.3390/land14040775
land-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Evaluation of Land Suitability for Construction in the Turpan–Hami Region Based on the Integration of the MaxEnt Model and Regional Planning

by
Guangpeng Zhang
1,
Li Zhang
2,
Alim Samat
3,4,5,
Yin Wu
6,*,
Wa Cao
6 and
Kaiyue Luo
1
1
College of Geography and Remote Sensing Science, Xinjiang University, Urumqi 830017, China
2
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
3
Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China
4
China-Kazakhstan Joint Laboratory for Remote Sensing Technology and Application, Al-Farabi Kazakh National University, Almaty 050012, Kazakhstan
5
University of Chinese Academy of Sciences, Beijing 100049, China
6
Xinjiang Uygur Autonomous Region Natural Resources Planning Research Institute, Urumqi 830011, China
*
Author to whom correspondence should be addressed.
Land 2025, 14(4), 775; https://doi.org/10.3390/land14040775
Submission received: 12 March 2025 / Revised: 27 March 2025 / Accepted: 2 April 2025 / Published: 4 April 2025
Browse Figures
Versions Notes

Abstract

:
Land resources are fundamental to regional economic development and ecological protection. As a critical tool for the scientific allocation of land resources, land suitability evaluation plays a pivotal role in achieving sustainable development goals. This study integrates the MaxEnt model with regional planning to conduct a multi-period evaluation of the construction land suitability in the Turpan–Hami region, aiming to elucidate the distribution patterns of suitability and their driving mechanisms across different historical periods. By synthesizing natural geographic and socioeconomic data, a comprehensive suitability evaluation framework was developed, enabling a multi-temporal analysis of construction land suitability from 2000 to 2023. The results revealed a clear trend of optimization in construction land suitability within the Turpan–Hami region, characterized by the continuous expansion of highly suitable areas and a significant reduction in unsuitable areas, with the regional suitability distribution becoming increasingly balanced over time. The population density, GDP, and road density were identified as the primary drivers of suitability distribution, with the population density exerting the most substantial influence. Among the natural environmental factors, the Normalized Difference Vegetation Index (NDVI) imposed significant constraints on the land suitability, particularly in ecologically sensitive areas. This study innovatively applied the MaxEnt model to the evaluation of construction land suitability, integrating it with regional planning to comprehensively assess the spatial distribution and dynamic changes in land suitability in the Turpan–Hami region. Furthermore, this research aligns closely with policy frameworks, fully considering the impacts of ecological and agricultural protection constraints within regional planning policies on the suitability distribution, and it explores optimized land use strategies under policy guidance. The findings provide a robust scientific foundation for the efficient allocation of land resources and the enhancement of ecological protection in the Turpan–Hami region.

1. Introduction

Land resources are the foundation of regional economic and social development, and land suitability evaluation, as an important tool for land resource management, plays a significant role in achieving sustainable development [1]. With the rapid economic growth and urbanization in China, the demand for land resources continues to rise, leading to increasing pressure on land development and the heightened vulnerability of the ecological environment [2,3,4]. Therefore, scientifically evaluating the land suitability and rationally allocating limited land resources have become core tasks in the current land use management. Land development involves both the demand for construction land and the protection and utilization of agricultural land. Construction land suitability evaluation helps to guide urban expansion and infrastructure development, avoiding resource waste and ecological degradation caused by unplanned development [5]. Meanwhile, agricultural land suitability evaluation focuses on ensuring a balance between agricultural production and ecological protection, identifying the most suitable areas for agricultural activities to achieve sustainable agricultural development [6]. By integrating the suitability evaluations of these two types of land, a scientific foundation can be provided for land resource management in the Turpan–Hami region, optimizing the land use patterns and promoting the coordinated development of the economy, society, and the environment.
With the advancement of economic development and region-specific management, research on land suitability evaluation has gradually evolved toward a more comprehensive and refined framework, particularly focusing on personalized analyses tailored to the characteristics of specific regions. Currently, land suitability evaluation not only requires a detailed analysis of the regional characteristics but also demands comprehensive assessments that integrate the natural conditions, socioeconomic context, and ecological environment features of different areas [7]. Therefore, research on land suitability evaluation must consider not only natural environmental factors, such as the climatic conditions, soil types, and topography, but also integrate socioeconomic factors, including the regional economic development levels, industrial distribution, and infrastructure construction, to ensure that land development aligns with the requirements of sustainable development [8].
The concept of the “Three Lines” was first introduced in the “Provincial Spatial Planning Pilot Scheme” issued by the government in 2016 [9]. It includes three “lines”—ecological protection redlines, permanent basic farmland protection lines, and urban development boundaries—which align with previous planning concepts, such as “Three Life Spaces” [10]. The “Three Lines” emphasize rigid boundary control, reflecting a “bottom-line” control approach, requiring clear boundaries and content to facilitate management and ensure the systematization of spatial structures [11]. The delineation of the “Three Lines” not only helps to optimize land resource allocation but also ensures coordination between regional development and ecological protection, based on respect for the regional natural conditions and socioeconomic characteristics [12]. In the process of evaluating construction land suitability, integrating the “Three Lines” concept can effectively combine the requirements of land development with those of ecological protection, agricultural development, and other aspects, thereby forming a scientific regional planning framework [13].
The MaxEnt model is a machine learning-based spatial suitability assessment tool that is widely used in the fields of environmental science, ecology, and land resource management [14,15]. The MaxEnt model is fundamentally grounded in the principle of maximum entropy, which seeks to estimate the least biased probability distribution based on the available data. Its core concept involves leveraging known geographic distribution data and environmental variables to predict the suitability distribution of unknown areas [16,17]. Specifically, the MaxEnt model maximizes the entropy to ensure that the predicted distribution aligns most closely with known conditions while retaining the highest level of information. This feature makes the MaxEnt model highly suitable for land suitability assessments, as it operates without strict distributional assumptions, effectively handles incomplete data, and delivers robust predictions in highly uncertain environments [18,19].
The advantage of the MaxEnt model in land suitability evaluation lies in its ability to integrate multiple spatial datasets and generate high-precision suitability predictions [20]. Compared to traditional spatial analysis methods, such as regression analysis and statistical models, the MaxEnt model can simultaneously process multiple environmental variables, fully accounting for factors such as geography, climate, soil, and vegetation. This approach performs well not only under conditions of complete data but also provides reliable evaluation results in cases of incomplete data, sparse samples, or an uneven distribution [21]. For instance, in land suitability evaluation, MaxEnt can integrate remote sensing imagery, climate data, soil types, and socioeconomic factors to establish relationships between different variables, enabling a more comprehensive analysis of the regional suitability [22].
With the continuous development and improvement of tools and instruments such as remote sensing technology, satellite imagery, drone monitoring, and ground observation stations, data products are being constantly updated [23]. Firstly, the long-term temporal sequence of data provides the possibility for dynamic analysis in land suitability evaluation. Long-term time series data, by offering continuous time-point data to the model, enable land suitability assessments to reflect the dynamic evolution of land suitability across different time periods under the influence of factors such as socioeconomic development, climate change, and policy adjustments. This temporal characteristic of the data offers a more comprehensive perspective for land resource management, allowing researchers to analyze the varying performance of land suitability at different time points. It further facilitates the identification of key factors and patterns influencing changes in land suitability over time [24].
Secondly, the diversity of data enhances the comprehensiveness and precision of land suitability evaluation. Remote sensing imagery provides high-resolution spatial data, which accurately reflect various types of surface information [25]. Additionally, socioeconomic data products, derived from long-term statistical yearbooks and surveys, allow the evaluation to not only consider natural environmental factors but also incorporate socioeconomic variables such as the regional economic development and industrial distribution [26]. This data diversity ensures that land suitability evaluations comprehensively reflect ecological, social, and economic factors, thereby improving the scientific validity and accuracy of the results [27]. Furthermore, annual land use data compiled by natural resource departments provide a robust data foundation for the MaxEnt model. Land use data, meticulously categorized for construction land by national and local natural resource management agencies, offer precise classifications, providing a reliable basis for land suitability evaluations [28].
Turpan and Hami, located in Northwest China along the Silk Road Economic Belt, serve as key nodes connecting Central Asia. Under the frameworks of the Belt and Road Initiative and the Western Development Strategy, the Turpan–Hami region has benefited from substantial policy support, fostering continuous infrastructure development and economic expansion. These advancements have significantly accelerated the region’s urbanization process [29]. Rapid urbanization has created an urgent need for the development and rational utilization of land resources [30]. In this context, this study focuses on Turpan and Hami, utilizing the MaxEnt model under the framework of the “Three Lines” planning concept. By integrating various datasets, including climate, soil, and socioeconomic factors, this study analyzes the suitability of construction land in Turpan and Hami. By conducting multi-temporal suitability assessments, this study analyzes the evolving trends in land suitability and investigates the key factors driving these changes.
Furthermore, based on the evaluation results, this study not only provides targeted recommendations for the development planning of the Turpan–Hami region to promote regional sustainable development and ecological conservation but also offers a replicable research framework for other arid and ecologically vulnerable regions worldwide. By leveraging the “Three Lines” planning framework, this study employs the MaxEnt model to integrate climate, soil, and socioeconomic factors for land suitability assessment. This methodological approach is not only applicable to the Turpan–Hami region but also serves as a scientifically grounded framework for land use evaluation in other similar regions. Different areas can adapt this approach based on their specific policy contexts and environmental conditions to optimize land development planning and enhance the resource allocation efficiency.

2. Materials and Methods

2.1. Study Area

The Tuha region is located in Eastern Xinjiang (41°12′–45°05′ N, 87°16′–96°23′ E), as shown in Figure 1. It mainly includes the administrative areas of Turpan and Hami, with Turpan comprising three county-level divisions and Hami comprising three county-level divisions. The total area of the region is approximately 2.1 × 105 km2, with the elevation ranging from −194 m to 4881 m. The primary land use types include cultivated land, forest land, grassland, water bodies, construction land, and unused land [31]. The region is rich in coal resources [32]. The entire Tuha region lies within an arid zone, characterized by a typical continental arid climate with significant diurnal temperature variations, low precipitation, and high evaporation. It faces severe water scarcity, land desertification, sparse vegetation, and low ecological and land reserve resource indices, leading to high ecological pressure and a complex relationship between land reserve development and the ecological environment. Additionally, due to its unique geographical location, this region plays a pivotal role in the cooperation between China and Central Asia [33].

2.2. Construction of the Evaluation Index System

The suitability of construction land is influenced by multiple factors, including the population, economy, transportation, topography, vegetation, and soil conditions [34]. To accurately predict the spatial patterns of construction land suitability, the selection of indicators should be based on these factors and involve a comprehensive analysis from multiple disciplinary perspectives to achieve a balance between economic development and rational resource utilization. Based on existing research findings and the natural and social conditions of the Turpan–Hami region, this study constructed an evaluation index system, as shown in Table 1. These indicators comprehensively reflect the overall natural and social conditions of the Turpan–Hami region, providing a solid data foundation for the precise evaluation of the construction land suitability.

2.3. Method

2.3.1. Suitability Evaluation Model and Method

This study utilizes the MaxEnt model to evaluate the suitability of construction land in the Turpan–Hami region. The required data included land use sample data and related environmental variable data. Sample data were derived from land use polygon data at six time points (2000, 2005, 2010, 2015, 2020, and 2023). Data for 2000 and 2005 were supplemented by remote sensing image interpretation to ensure sufficient land use samples. Construction land samples were extracted from the land use data, with a uniform grid resolution of 500 m. The environmental variables encompassed natural geographic factors (e.g., elevation, slope, soil type), climatic conditions (e.g., annual mean temperature, precipitation, sunshine hours), and socioeconomic factors (e.g., population density, GDP). The sources of these data are detailed in Table 1. To avoid multicollinearity among the variables, a Pearson correlation analysis was applied (|r| < 0.9), and selected variables were standardized to the study area. Missing data were interpolated using ArcGIS spatial interpolation methods.
For model operation, 70% of the samples were used for training and 30% for validation. Model parameters were set with a regularization multiplier of 1 and a maximum number of iterations of 500. Model accuracy was validated using the area under the curve (AUC) of the receiver operating characteristic (ROC). Finally, the results generated by the MaxEnt model were overlaid with ecological protection boundaries and permanent basic farmland protection areas, as delineated by the “Three Zones and Three Lines” framework established by the natural resource departments. This analysis provided the suitability results for construction land in the Turpan–Hami region; it was followed by a performance assessment of the model and an analysis of the spatiotemporal changes in suitability. Based on the evaluation results, relevant policy recommendations were proposed. The technical workflow is illustrated in Figure 2.

2.3.2. Suitability Level Transformation Analysis

In this study, the land suitability in the research area was classified into four levels: unsuitable, marginally suitable, moderately suitable, and highly suitable. Two time periods, 2000–2010 and 2010–2023, were selected to analyze the dynamic changes in the suitability levels through a transition analysis. The specific methodology is as follows. First, using the raster calculation tools in ArcGIS 10.2, a suitability transition matrix was constructed to quantify the transitions between different suitability levels during the two time periods. The matrix recorded the transition areas and proportions, revealing the dynamic changes between various levels. Second, to clearly visualize the dynamic transformation trends of the suitability levels, Sankey diagrams were employed to display the transition results across the selected time periods.

2.3.3. Analysis of Suitability Geospatial Change Trends

To clarify the development trends of land suitability in the study area, this study performed an overlay analysis of the suitability evaluation results across multiple time periods to assess the dynamic changes in suitability, i.e., whether it improved from low to high levels or deteriorated from high to low levels. Based on the temporal changes in the land suitability levels, a change trend evaluation formula was constructed as follows [35]:
Y = X 2023 × 100 + X 2010 × 10 + X 2000 × 1
Here, X 2000 , X 2010 , and X 2023 represent the suitability levels in 2000, 2010, and 2023, respectively. The suitability levels are defined as follows: 1 (Unsuitable), 2 (Marginally suitable), 3 (Moderately suitable), and 4 (Highly suitable). For example, if the suitability change value for a certain area is “321”, it indicates that the area was unsuitable in 2000, moderately suitable in 2010, and highly suitable in 2023, demonstrating a gradual improvement in suitability. Conversely, if the change value is “123”, it suggests a gradual decline in suitability over time.

3. Results

3.1. Analysis of Model Performance and Suitability Driving Factors

The evaluation results indicate that the MaxEnt model exhibits high predictive accuracy in assessing the suitability of construction land in the Turpan–Hami region. The average area under the curve (AUC) values calculated for the six time points all exceeded 0.92, as shown in Figure 3. Moreover, the AUC values for each year were significantly higher than the reference value of 0.5 for a random model, demonstrating that the model reliably predicts the distribution of construction land suitability across different time points. Additionally, an analysis of the model deviation revealed the bias values for the six years to be 0.002 (2000), 0.001 (2005), 0.004 (2010), 0.008 (2015), 0.012 (2020), and 0.005 (2023). Among these, the AUC value for 2005 was the highest, with the smallest deviation, indicating optimal prediction stability and accuracy for that year. In contrast, the AUC value for 2020 was the lowest, and the standard deviation for 2015 was the largest on average, although both still remained within the range of high precision. Overall, the model demonstrated high applicability and reliability across the six evaluation periods from 2000 to 2023, providing robust scientific support for the suitability evaluation of construction land in the Turpan–Hami region.
The suitability of construction land in the Turpan–Hami region is primarily influenced by a combination of factors, including the population density, GDP, road density, land use diversity, slope, and elevation. The model results indicate that the population density is the most critical driving factor for construction land suitability, consistently showing the strongest influence among all factors across the six time points, as shown in Figure 4. This highlights the significant role of population agglomeration in shaping the spatial distribution of construction land during the urbanization process. The GDP is the second most important factor after the population density, with its contribution peaking between 2005 and 2015. This suggests that economic activities and the regional industrial layout play a crucial role in guiding construction land development. Although the importance of the road density fluctuated across the years, it maintained a consistently strong influence, reflecting the long-term support of transportation infrastructure in determining the construction land layout. Roads are particularly critical in promoting land development and connecting economic activities.
Land use types also demonstrated significant and stable importance, with little variation in their influence over the years. This indicates that their impact acts as a fundamental constraint, primarily limiting construction land selection due to the spatial distribution of different land types (e.g., farmland, forest land, and grassland). Among the natural resource factors, the NDVI had a relatively large impact on the construction land suitability, whereas the slope and soil depth had relatively minor effects. The importance of the NDVI lies in its ability to reflect the vegetation coverage in a region. Areas with high NDVI values are often ecologically sensitive and unsuitable for construction development. Given the fragile ecological environment of the Turpan–Hami region, vegetation coverage has become a critical constraint on the layout of construction land.

3.2. Spatiotemporal Characteristics of Construction Land Suitability

Based on the evaluation results regarding the construction land suitability for the years 2000, 2005, 2010, 2015, 2020, and 2023, the overall trend of construction land suitability in the study area has shown continuous optimization. The area of suitable regions has significantly increased, with their spatial distribution gradually expanding and adjusting over time. In 2000, the highly suitable regions were primarily concentrated in the central part of the study area, forming relatively contiguous clusters, as shown in Figure 5 and Figure 6. Moderately suitable regions were relatively scarce, while marginally suitable and unsuitable regions occupied the majority of the study area, indicating an overall low level of construction land suitability. By 2005, the distribution pattern of suitable regions had improved, with a significant increase in the area of moderately suitable regions. The highly suitable regions remained stable, while the area of unsuitable regions began to decrease. In 2010, the construction land suitability improved markedly, with the highly suitable regions further expanding into the central and eastern parts of the study area. The area of moderately suitable regions continued to grow, while the area of unsuitable regions decreased, suggesting a strong relationship between regional development and suitability improvement.
By 2015, the areas of highly suitable and moderately suitable regions continued to expand, particularly in the central and southwestern parts of the study area, showing significant optimization. The area of marginally suitable regions decreased compared to the previous periods, while the area of unsuitable regions further contracted. The spatial pattern of suitability showed further optimization. During the periods of 2020 and 2023, the areas of highly suitable and moderately suitable regions reached their peaks within the study period. As summarized in Table 2, the distribution of suitable regions expanded outward from the central part of the study area, with the spatial continuity further enhanced. The area of unsuitable regions decreased to its lowest level, demonstrating significant overall improvements in regional suitability. In particular, the improvement in suitability was most evident in the central and southeastern parts of the study area in 2023. Overall, from 2000 to 2023, the construction land suitability underwent a continuous process of optimization. The area of suitable regions significantly increased, as shown in Figure 5, with a more balanced spatial distribution, while the area of unsuitable regions gradually declined. This reflects the steady progress in regional development and land use optimization across the study area.
The suitability levels of construction land in the Turpan–Hami region experienced significant dynamic changes over the study period. The transitions among different suitability levels reflect a general trend of gradual optimization, as shown in Figure 7. A notable proportion of low-suitability areas transitioned to higher-suitability areas, with a significant share of unsuitable areas converting to regions of higher suitability. This indicates that, over time, the overall suitability of construction land in the region has shown an improving trend. Meanwhile, areas of higher suitability exhibited strong spatial stability, with only a small portion experiencing degradation and transitioning to lower suitability levels. It is worth noting that direct transitions from the lowest suitability level to the highest level occurred infrequently, suggesting that significant improvements in suitability are largely dependent on gradual accumulation and sustained external interventions, such as ecological restoration and the optimization of regional planning.
In terms of the transition characteristics, the changes in the suitability levels involved both continuous optimization from unsuitable to higher-suitability areas and some degree of fluctuation. For instance, certain low-suitability areas exhibited temporary improvements during specific periods before degrading again. Overall, this transition process reflects the complexity of the dynamic evolution of construction land suitability, although the trend toward regional optimization remains dominant. This study highlights that the gradual optimization of the construction land suitability is not only driven by improvements in the natural conditions but also influenced by a combination of factors, such as land use planning and socioeconomic development. The dynamic data from these six periods clearly reveal the process of transitioning from unsuitability to higher suitability in the region and further confirm the positive interaction between regional development and an improvement in land suitability.

3.3. Geospatial Trend Analysis of Suitability Changes

From the geospatial trend of construction land suitability changes, it can be observed that, although the proportion of positive changes in suitability remains limited in terms of area, their distribution is concentrated in the central urban built-up areas and their surrounding regions, as shown in Figure 8. In particular, the core areas, such as Turpan’s Gaochang District and Hami’s Yi Prefecture, have experienced significant improvements in their suitability levels due to the gradual enhancement of infrastructure, improved transportation conditions, and the agglomeration of economic activities, reflecting the positive dynamics of urbanization. Simultaneously, the suitability of newly developed areas, such as those along major transportation corridors and industrial parks, has also improved, highlighting the role of regional economic development in driving land use optimization.
In contrast, areas with negative changes, while scattered and occupying a very small proportion of the total area, are primarily concentrated in ecologically fragile peripheral zones and a few regions where overdevelopment or insufficient resource conditions prevail. This development pattern, characterized by significant suitability improvements in key areas, demonstrates the positive progress of construction land development under policy support and optimized resource allocation. However, it also underscores the need for future land use planning to further strengthen the protection of ecologically sensitive areas, ensuring the harmonious coexistence of regional development and ecological preservation.

4. Discussion

4.1. Geospatial Trend Analysis of Suitability Development

The MaxEnt model is a machine learning method based on niche theory, with its core predictive principle being the exploration of the relationship between a species’ spatial distribution data and surrounding environmental variables to predict its potential suitable geographic distribution [36]. The model relies solely on presence-only data and does not require absence data. It uses automated calculations to reveal the contributions and importance of environmental variables to the suitability distribution and identifies the suitable ranges of these variables. This characteristic makes the MaxEnt model highly applicable in scenarios with limited data or complex environments [37].
In this study, the MaxEnt model was applied for the first time to evaluate the suitability of construction land in the Turpan–Hami region, demonstrating strong alignment between the model’s predictive principles and the characteristics of the study area. Construction land suitability is analogous to species habitats, as its distribution is influenced by a combination of natural factors (e.g., slope, vegetation cover, elevation) and socioeconomic factors (e.g., road density, population distribution, GDP) [38]. By analyzing the contribution rates of variables and identifying suitable ranges through the model, the roles of different variables in the distribution of construction land suitability were clarified, providing a scientific basis for land use planning in the Turpan–Hami region. Furthermore, by utilizing high-quality input data, such as land use data extracted from remote sensing imagery and transportation infrastructure distribution data, the model successfully quantified the spatial distribution of suitable land areas. This approach avoided potential biases associated with traditional subjective weighting methods, thereby enhancing the accuracy and reliability of the evaluation [39].
However, the model still has certain limitations in practical applications. First, the MaxEnt model is highly dependent on the quality and resolution of the input data [40]. In this study, the socioeconomic data (e.g., population distribution, GDP) used could reflect the regional characteristics to some extent, but issues such as outdated temporal updates and an insufficient spatial resolution limit the ability to accurately capture local features, which may introduce bias into the model’s predictions. Second, the parameter settings of the MaxEnt model (e.g., regularization multiplier, number of background points) significantly influence the stability and accuracy of the predictions. However, the process of tuning these parameters lacks a unified standard. In regions with complex ecological and socioeconomic conditions, insufficient parameter optimization may restrict the model’s performance in regional adaptations [41].
To address these limitations, future research should focus on three key areas for improvement: (1) introducing high-resolution and dynamically updated data sources to further enhance the precision of socioeconomic and natural environmental variables; (2) integrating dynamic modeling methods (e.g., CA-MARKOV or FLUS models) to simulate the spatiotemporal dynamics of suitability changes [42]; and (3) conducting multi-regional experimental validation and parameter optimization to develop standardized models that are adaptable to diverse scenarios, thereby improving the applicability and predictive capability of the MaxEnt model in complex regions.

4.2. Suitability Driving Mechanisms and Policy Implications

The distribution of the construction land suitability in the Turpan–Hami region is the result of the combined influence of natural environmental factors, socioeconomic conditions, and policy interventions. This study reveals that the population density, GDP, and road density are the key socioeconomic drivers shaping the spatial patterns of construction land suitability. The land use type, as a fundamental constraint variable, has maintained a stable influence on the suitability distribution across different years. Meanwhile, the NDVI in the natural environment acts as a significant limiting factor for suitability in ecologically sensitive areas, whereas the effects of the slope and soil depth are relatively minor. These variables collectively determine the dynamic evolution of land suitability [43,44].
Planning has played a critical role in optimizing the distribution of land suitability. The “Three Lines” planning concept, by delineating ecological red lines and permanent basic farmland protection areas, has provided guidance and regulation for the layout of construction land in the Turpan–Hami region [45]. On the one hand, the policy has effectively curbed disorderly development in unsuitable areas, safeguarding ecologically sensitive zones. On the other hand, it has prioritized development in high-suitability areas, thereby supporting regional economic growth. However, this study also identified that certain areas, due to insufficient infrastructure and weak economic conditions, have persistently low suitability levels. This limits the potential for land development and exacerbates regional imbalances in development.
Future policies should focus more on region-specific guidance. In high-suitability areas, efforts should prioritize improving the land development efficiency and optimizing the industrial layout [46]. In moderate-suitability areas, policies should focus on improving the infrastructure, particularly the transportation networks, water supply, and public services, to unlock the regional development potential. Strategic investment in these areas can enhance the connectivity with high-suitability zones, facilitating economic spillover effects and balanced regional development. In marginally suitable areas, controlled development strategies should be adopted, emphasizing ecological conservation and sustainable land use practices. Small-scale, low-impact industries such as eco-tourism and sustainable agriculture can be encouraged to ensure economic viability while minimizing environmental degradation. Policies should also support land rehabilitation programs to gradually improve the land conditions.
In unsuitable areas, strict development restrictions should be maintained, with a primary focus on ecological restoration and environmental protection. Initiatives such as afforestation, soil conservation, and biodiversity protection should be prioritized. Additionally, policies should promote ecological compensation mechanisms to balance conservation efforts with regional socioeconomic development.

4.3. Future Research Directions

Future research should adopt a multidimensional and broader perspective to further refine construction land suitability evaluation methods based on the MaxEnt model and expand its application in national policies and regional practices. At the data level, more high-resolution, multi-temporal dynamic data sources should be incorporated [47]. These datasets would enable the more comprehensive capture of the spatiotemporal characteristics of natural and socioeconomic factors, thereby enhancing the model’s ability to analyze the distribution patterns of construction land suitability [48]. Particularly in regions like the Turpan–Hami area, characterized by complex ecological conditions and rapid urbanization, the integration of high-precision data can better delineate the balance between regional development and ecological conservation [49]. Research should also take a macro-level perspective by integrating suitability evaluations into the context of national policies for region-specific development strategies.
Although the “Three Lines” planning concept provides a general framework for land use planning across China, the diverse natural conditions and development demands of different regions present significant variations [50,51]. Future studies could explore region-specific optimization methods within the framework of “Three Lines” planning. By tailoring the suitability evaluation indicators and model parameters to the regional characteristics, the evaluation results can be aligned more closely with the local realities under the national policy framework [52]. For instance, in resource-based cities, suitability evaluation should focus more on changes in the industrial structure and resource dependency [53]. In ecological conservation areas, greater emphasis should be placed on the impact of ecological constraints on suitability. This region-specific adjustment would allow for more precise alignment between suitability analysis and regional development under the guidance of national policies. Through such refinements, suitability evaluations could better support sustainable land use planning and development strategies across different regions [54].

5. Conclusions

This study conducted a spatiotemporal dynamic evaluation of the construction land suitability in the Turpan–Hami region using the MaxEnt model in conjunction with the “Three Lines” planning framework. The results indicate a clear trend of suitability optimization, with the area of highly suitable regions gradually expanding and the distribution of suitability becoming more balanced. The population density, GDP, and road density were identified as the key socioeconomic drivers of the suitability distribution, with the population density exerting the most significant influence. This reflects the dominant spatial effect of population agglomeration during the urbanization process. Among the natural environmental factors, the NDVI acted as a limiting factor for the suitability distribution, particularly in ecologically sensitive areas, where vegetation cover played a critical role.
In addition, the “Three Lines” planning concept has significantly contributed to the optimization of the construction land suitability distribution. By delineating ecological red lines and permanent basic farmland protection areas, the policy has effectively restricted development in unsuitable areas, preventing the further degradation of ecologically sensitive zones caused by disorderly development. This has promoted more standardized and scientific regional land use. However, this study also identified slower improvements in suitability in some peripheral areas due to insufficient infrastructure and lagging economic development. These differences highlight the inherent disparities in the natural conditions and development potential within the Turpan–Hami region and point to key priorities for regional suitability optimization. Future efforts should enhance the support for low-suitability areas within the “Three Lines” planning framework, tailored to the regional characteristics, to achieve coordinated regional development and sustainable land resource utilization.
Methodologically, this study employed the MaxEnt model to integrate natural environmental and socioeconomic factors with the “Three Lines” planning framework, providing a scientific basis for the evaluation of the construction land suitability in the Turpan–Hami region. By analyzing the contribution rates of the variables, this study identified the critical driving roles of the population density, GDP, and road density in the suitability distribution. Moreover, by overlaying policy boundaries (ecological red lines and permanent basic farmland protection areas), this study effectively assessed the guiding role of policy implementation in optimizing land suitability. However, the research also revealed the model’s strong dependence on the resolution of the input data. The insufficient spatial and temporal resolutions of some socioeconomic and environmental data may have limited the detailed characterization of suitability patterns.
Therefore, future studies should incorporate higher-resolution data to further improve the accuracy and reliability of suitability evaluations. The results also underscore the need to address regional differences in the suitability distribution by aligning national policies with local practices. Tailored land use management strategies should be developed based on the natural conditions and development needs of different regions to achieve a harmonious balance between ecological conservation and economic growth. In conclusion, this study integrated socioeconomic and natural environmental factors within the framework of the “Three Lines” planning concept to comprehensively reveal the spatial patterns and spatiotemporal dynamics of construction land suitability in the Turpan–Hami region. The findings provide scientific support for the optimization of land resource allocation, ecological conservation, and sustainable regional development in the Turpan–Hami region. Furthermore, they offer theoretical insights and a practical reference for land suitability evaluations in other similar regions.

Author Contributions

Conceptualization, G.Z. and Y.W.; methodology, G.Z., L.Z. and A.S.; software, G.Z.; validation, G.Z., W.C. and L.Z.; formal analysis, G.Z., A.S. and Y.W.; investigation, G.Z., W.C. and K.L.; resources, Y.W.; data curation, G.Z. and Y.W.; writing—original draft preparation, G.Z.; writing—review and editing, G.Z., Y.W., W.C. and K.L.; visualization, G.Z.; supervision, W.C. and K.L.; project administration, Y.W.; funding acquisition, Y.W. All authors have read and agreed to the published version of the manuscript.

Funding

Supported by the Third Xinjiang Scientific Expedition Program (Grant No. 2022xjkk1100).

Data Availability Statement

The data utilized in this research can be obtained from the corresponding authors upon request.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Nkonya, E.M.; Karsenty, A.; Souza, C., Jr.; Shah, M.; von Braun, J.; Galford, G.; Park, S. Sustainable Land Use for the 21st Century. 2012. Available online: https://cgspace.cgiar.org/server/api/core/bitstreams/6ebfb567-bb52-4261-80a8-097767ecb182/content (accessed on 2 April 2025).
  2. Sun, M.; Wang, J.; He, K. Analysis on the urban land resources carrying capacity during urbanization—A case study of Chinese YRD. Appl. Geogr. 2020, 116, 102170. [Google Scholar]
  3. Wu, Y.; Zhang, X.; Shen, L. The impact of urbanization policy on land use change: A scenario analysis. Cities 2011, 28, 147–159. [Google Scholar] [CrossRef]
  4. Yeh, K. China’s economic growth: Recent trends and prospects. In Rand-Publications-Mr-All Series; 2001; pp. 69–98. Available online: https://www.rand.org/content/dam/rand/pubs/monograph_reports/2006/MR1300.pdf#page=79 (accessed on 18 June 2024).
  5. Luo, W.; Bai, H.; Jing, Q.; Liu, T.; Xu, H. Urbanization-induced ecological degradation in Midwestern China: An analysis based on an improved ecological footprint model. Resour. Conserv. Recycl. 2018, 137, 113–125. [Google Scholar] [CrossRef]
  6. de Macedo, L.S.V.; Picavet, M.E.B.; de Oliveira, J.A.P.; Shih, W.-Y. Urban green and blue infrastructure: A critical analysis of research on developing countries. J. Clean. Prod. 2021, 313, 127898. [Google Scholar] [CrossRef]
  7. Zhang, Z.; Li, J. Spatial suitability and multi-scenarios for land use: Simulation and policy insights from the production-living-ecological perspective. Land Use Policy 2022, 119, 106219. [Google Scholar]
  8. Wilkerson, M.L.; Mitchell, M.G.; Shanahan, D.; Wilson, K.A.; Ives, C.D.; Lovelock, C.E.; Rhodes, J.R. The role of socio-economic factors in planning and managing urban ecosystem services. Ecosyst. Serv. 2018, 31, 102–110. [Google Scholar]
  9. Ye, B.; Zheng, X.; Luo, H.; Shen, J.; Ji, F.; Lin, X. Coordinated Delineation of “Three Districts and Three Lines”: Anatomy of the Phenomenon, Technical Logic and Nanjing’s Experience. Available online: https://upforum.wupen.org/Assets/userfiles/files/issues/2024/2024-03/2024-04/7-%E8%8B%B1%E8%AF%AD.pdf (accessed on 1 April 2025).
  10. Zang, Z.; Zou, X.; Xi, X.; Zhang, Y.; Zheng, D.; Sun, C. Quantitative characterization and comprehensive evaluation of regional water resources using the Three Red Lines method. J. Geogr. Sci. 2016, 26, 397–414. [Google Scholar]
  11. Yi, J.; Yi, D.; Tang, Y.; Guo, J.; Ou, M.; Cheng, X. Building a More Secure Territory Spatial Pattern in China: An Analysis Based on Human-Environment Interactions. Land 2023, 12, 2137. [Google Scholar] [CrossRef]
  12. Peng, J.; Du, Y.; Liu, Y.; Hu, X. How to assess urban development potential in mountain areas? An approach of ecological carrying capacity in the view of coupled human and natural systems. Ecol. Indic. 2016, 60, 1017–1030. [Google Scholar]
  13. Opdam, P.; Steingröver, E.; Van Rooij, S. Ecological networks: A spatial concept for multi-actor planning of sustainable landscapes. Landsc. Urban Plan. 2006, 75, 322–332. [Google Scholar]
  14. Phang, W.K.; Hamid, M.H.b.A.; Jelip, J.; Mudin, R.N.b.; Chuang, T.-W.; Lau, Y.L.; Fong, M.Y. Predicting Plasmodium knowlesi transmission risk across Peninsular Malaysia using machine learning-based ecological niche modeling approaches. Front. Microbiol. 2023, 14, 1126418. [Google Scholar]
  15. Sari, F.; Yalcin, M. Investigation of the importance of criteria in potential wind farm sites via machine learning algorithms. J. Clean. Prod. 2024, 435, 140575. [Google Scholar]
  16. Harte, J.; Newman, E.A. Maximum information entropy: A foundation for ecological theory. Trends Ecol. Evol. 2014, 29, 384–389. [Google Scholar] [PubMed]
  17. Phillips, S.J.; Dudík, M. Modeling of species distributions with Maxent: New extensions and a comprehensive evaluation. Ecography 2008, 31, 161–175. [Google Scholar]
  18. Merow, C.; Smith, M.J.; Silander, J.A., Jr. A practical guide to MaxEnt for modeling species’ distributions: What it does, and why inputs and settings matter. Ecography 2013, 36, 1058–1069. [Google Scholar]
  19. Radosavljevic, A.; Anderson, R.P. Making better Maxent models of species distributions: Complexity, overfitting and evaluation. J. Biogeogr. 2014, 41, 629–643. [Google Scholar]
  20. Akpoti, K.; Kabo-bah, A.T.; Zwart, S.J. Agricultural land suitability analysis: State-of-the-art and outlooks for integration of climate change analysis. Agric. Syst. 2019, 173, 172–208. [Google Scholar]
  21. Elith, J.; Phillips, S.J.; Hastie, T.; Dudík, M.; Chee, Y.E.; Yates, C.J. A statistical explanation of MaxEnt for ecologists. Divers. Distrib. 2011, 17, 43–57. [Google Scholar]
  22. Wang, Y.; Chao, B.; Dong, P.; Zhang, D.; Yu, W.; Hu, W.; Ma, Z.; Chen, G.; Liu, Z.; Chen, B. Simulating spatial change of mangrove habitat under the impact of coastal land use: Coupling MaxEnt and Dyna-CLUE models. Sci. Total Environ. 2021, 788, 147914. [Google Scholar]
  23. Toth, C.; Jóźków, G. Remote sensing platforms and sensors: A survey. ISPRS J. Photogramm. Remote Sens. 2016, 115, 22–36. [Google Scholar]
  24. Kumar, G.; Nath, V.; Mandal, U.; Sena, D.R.; Pongener, A.; Ranjan, R.; Madhu, M. Climate and soil suitability zonation for Litchi (Litchi chinensis) in India using geo-science tool-based analytical hierarchy process. Egypt. J. Remote Sens. Space Sci. 2023, 26, 581–594. [Google Scholar]
  25. Zheng, X.; Zhang, W.; Deng, H.; Zhang, H. County-Level Poverty Evaluation Using Machine Learning, Nighttime Light, and Geospatial Data. Remote Sens. 2024, 16, 962. [Google Scholar] [CrossRef]
  26. Sakti, A.D.; Anggraini, T.S.; Ihsan, K.T.N.; Misra, P.; Trang, N.T.Q.; Pradhan, B.; Wenten, I.G.; Hadi, P.O.; Wikantika, K. Multi-air pollution risk assessment in Southeast Asia region using integrated remote sensing and socio-economic data products. Sci. Total Environ. 2023, 854, 158825. [Google Scholar] [CrossRef]
  27. Zhang, Z.; Gong, J.; Li, J.; Yang, J.; Chen, G.; Ren, Y.; Plaza, A. Comparative study of construction land development suitability assessment: Insights from multiple models and driving forces. Environ. Impact Assess. Rev. 2024, 107, 107574. [Google Scholar]
  28. Chrisman, N.R. The accuracy of map overlays: A reassessment. Landsc. Urban Plan. 1987, 14, 427–439. [Google Scholar] [CrossRef]
  29. Kang, L.; Jia, Y.; Zhang, S. Spatiotemporal distribution and driving forces of ecological service value in the Chinese section of the “Silk Road Economic Belt”. Ecol. Indic. 2022, 141, 109074. [Google Scholar]
  30. Xia, J.; Zhang, Y.; Xiong, L.; He, S.; Wang, L.; Yu, Z. Opportunities and challenges of the Sponge City construction related to urban water issues in China. Sci. China Earth Sci. 2017, 60, 652–658. [Google Scholar] [CrossRef]
  31. Liu, Z.; Wang, J.; Ding, J.; Xie, X. Analysis of spatial–temporal evolution trends and influential factors of desert-oasis thermal environment in typical arid zone: The case of Turpan–Hami region. Ecol. Indic. 2023, 154, 110747. [Google Scholar] [CrossRef]
  32. Han, S.; Zhang, J.; Zhou, Y.; Bai, S.; Huang, L.; Wang, C.; Huang, W. Formation and accumulation of lower Jurassic tight gas sands field in Kekeya area of Tuha Basin, northwestern China. J. Nat. Gas Sci. Eng. 2016, 29, 101–109. [Google Scholar] [CrossRef]
  33. Kou, Y.; Chen, S.; Zhou, K.; Qiu, Z.; He, J.; Shi, X.; Zhou, X.; Zhang, Q. Spatiotemporal Patterns and Coupling Coordination Analysis of Multiscale Social–Economic–Ecological Effects in Ecologically Vulnerable Areas Based on Multi-Source Data: A Case Study of the Tuha Region, Xinjiang Province. Land 2024, 13, 282. [Google Scholar] [CrossRef]
  34. Ustaoglu, E.; Aydınoglu, A. Suitability evaluation of urban construction land in Pendik district of Istanbul, Turkey. Land Use Policy 2020, 99, 104783. [Google Scholar] [CrossRef]
  35. Zhou, H.; Na, X.; Li, L.; Ning, X.; Bai, Y.; Wu, X.; Zang, S. Suitability evaluation of the rural settlements in a farming-pastoral ecotone area based on machine learning maximum entropy. Ecol. Indic. 2023, 154, 110794. [Google Scholar] [CrossRef]
  36. Warren, D.L.; Seifert, S.N. Ecological niche modeling in Maxent: The importance of model complexity and the performance of model selection criteria. Ecol. Appl. 2011, 21, 335–342. [Google Scholar] [CrossRef] [PubMed]
  37. Bradie, J.; Leung, B. A quantitative synthesis of the importance of variables used in MaxEnt species distribution models. J. Biogeogr. 2017, 44, 1344–1361. [Google Scholar] [CrossRef]
  38. Gong, J.; Chen, W.; Liu, Y.; Wang, J. The intensity change of urban development land: Implications for the city master plan of Guangzhou, China. Land Use Policy 2014, 40, 91–100. [Google Scholar] [CrossRef]
  39. Wang, T.-C.; Lee, H.-D. Developing a fuzzy TOPSIS approach based on subjective weights and objective weights. Expert Syst. Appl. 2009, 36, 8980–8985. [Google Scholar] [CrossRef]
  40. Yackulic, C.B.; Chandler, R.; Zipkin, E.F.; Royle, J.A.; Nichols, J.D.; Campbell Grant, E.H.; Veran, S. Presence-only modelling using MAXENT: When can we trust the inferences? Methods Ecol. Evol. 2013, 4, 236–243. [Google Scholar] [CrossRef]
  41. Fernández, I.C.; Morales, N.S. One-class land-cover classification using MaxEnt: The effect of modelling parameterization on classification accuracy. PeerJ 2019, 7, e7016. [Google Scholar] [CrossRef]
  42. Zhang, H.; Li, H.; Zhang, J.; Wang, J.; Wang, G.; Shan, Y.; Zheng, H. Simulation of wetland distribution in the Yellow River Basin based on an improved Markov-FLUS model. Environ. Res. Lett. 2024, 19, 104001. [Google Scholar] [CrossRef]
  43. Xu, K.; Kong, C.; Li, J.; Zhang, L.; Wu, C. Suitability evaluation of urban construction land based on geo-environmental factors of Hangzhou, China. Comput. Geosci. 2011, 37, 992–1002. [Google Scholar]
  44. Xu, Y.; Wang, T.; Liu, W.; Zhang, R.; Hu, Y.; Gao, W.; Chen, Y. Rural system sustainability evaluation based on emergy analysis: An empirical study of 321 villages in China. J. Clean. Prod. 2023, 389, 136088. [Google Scholar]
  45. Yang, Y.; Bao, W.; Liu, Y. Coupling coordination analysis of rural production-living-ecological space in the Beijing-Tianjin-Hebei region. Ecol. Indic. 2020, 117, 106512. [Google Scholar]
  46. Huang, Z.; He, C.; Zhu, S. Do China’s economic development zones improve land use efficiency? The effects of selection, factor accumulation and agglomeration. Landsc. Urban Plan. 2017, 162, 145–156. [Google Scholar] [CrossRef]
  47. Townsend Peterson, A.; Papeş, M.; Eaton, M. Transferability and model evaluation in ecological niche modeling: A comparison of GARP and Maxent. Ecography 2007, 30, 550–560. [Google Scholar]
  48. Xie, Y.; Liu, C.; Chang, S.; Jiang, B. Urban sustainability: Integrating socioeconomic and environmental data for multi-objective assessment. Sustainability 2022, 14, 9142. [Google Scholar] [CrossRef]
  49. Li, Z.; Liu, Y.; Zeng, H. Application of the MaxEnt model in improving the accuracy of ecological red line identification: A case study of Zhanjiang, China. Ecol. Indic. 2022, 137, 108767. [Google Scholar]
  50. Zhao, Z.; Yang, K. Suitability matching evaluation of the low-carbon regional integrated energy system based on the “resource-demand” balance. Sustain. Energy Technol. Assess. 2024, 72, 104099. [Google Scholar]
  51. Reinhardt, J.; Liersch, S.; Abdeladhim, M.A.; Diallo, M.; Dickens, C.; Fournet, S.; Hattermann, F.F.; Kabaseke, C.; Muhumuza, M.; Mul, M.L. Systematic evaluation of scenario assessments supporting sustainable integrated natural resources management. Ecol. Soc. 2018, 23, 5. [Google Scholar] [CrossRef]
  52. 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]
  53. Chun, B.; Guldmann, J.-M. Spatial statistical analysis and simulation of the urban heat island in high-density central cities. Landsc. Urban Plan. 2014, 125, 76–88. [Google Scholar]
  54. Koc, K.; Ekmekcioğlu, Ö.; Özger, M. An integrated framework for the comprehensive evaluation of low impact development strategies. J. Environ. Manag. 2021, 294, 113023. [Google Scholar]
Land 14 00775 g001
Figure 1. The area of study.
Figure 1. The area of study.
Land 14 00775 g001
Land 14 00775 g002
Figure 2. Technology roadmap.
Figure 2. Technology roadmap.
Land 14 00775 g002
Land 14 00775 g003
Figure 3. ROC curve.
Figure 3. ROC curve.
Land 14 00775 g003
Land 14 00775 g004
Figure 4. Evaluation metrics’ feature importance.
Figure 4. Evaluation metrics’ feature importance.
Land 14 00775 g004
Land 14 00775 g005
Figure 5. Suitability distribution of construction land in the Turpan–Hami region during different periods.
Figure 5. Suitability distribution of construction land in the Turpan–Hami region during different periods.
Land 14 00775 g005
Land 14 00775 g006
Figure 6. (a) Suitability area statistics for different years; (b) area change trends in highly suitable and moderately suitable regions.
Figure 6. (a) Suitability area statistics for different years; (b) area change trends in highly suitable and moderately suitable regions.
Land 14 00775 g006
Land 14 00775 g007
Figure 7. Dynamic transformation maps between different suitability grades for the periods (a) 2000–2010 and (b) 2010–2023.
Figure 7. Dynamic transformation maps between different suitability grades for the periods (a) 2000–2010 and (b) 2010–2023.
Land 14 00775 g007
Land 14 00775 g008
Figure 8. Development and change trends in construction land suitability.
Figure 8. Development and change trends in construction land suitability.
Land 14 00775 g008
Table 1. Construction of the evaluation index system.
Table 1. Construction of the evaluation index system.
IndexData Source
ElevationNASA (SRTM dataset)
SlopeSRTM data calculations
GDPGeographic Data Sharing Infrastructure, Global Resources Data Cloud
(www.gis5g.com (accessed on 8 January 2024))
Population DensityGEE (WorldPop)
NDVIMOD13Q1 v006 dataset
FVCGeographic Data Sharing Infrastructure, Global Resources Data Cloud
(www.gis5g.com (accessed on 8 January 2024))
LAIGeographic Data Sharing Infrastructure, Global Resources Data Cloud
(www.gis5g.com (accessed on 8 January 2024))
Soil Particle Size DistributionData from the Second Soil Census
Soil Bulk DensityData from the Second Soil Census
Soil DepthData from the Second Soil Census
Land UseGeographic Data Sharing Infrastructure, Global Resources Data Cloud
(www.gis5g.com (accessed on 8 January 2024))
Road DensityGeographic Data Sharing Infrastructure, Global Resources Data Cloud
(www.gis5g.com (accessed on 8 January 2024))
Table 2. Suitability area statistics (km2).
Table 2. Suitability area statistics (km2).
Suitability Level201020052010201520202023
Highly suitable375.5354.2211,888.5199,697.2198,593.1204,628.4
Moderately suitable516.4537.91864.43503.53545.43785.8
Marginally suitable1079.4918.32752.112,779.712,710.46831.4
Unsuitable215,812.2215,972.1211,888.5199,697.2198,593.1204,628.4
Total217,783.4217,783.4217,783.4217,783.4217,783.4217,783.4
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Zhang, G.; Zhang, L.; Samat, A.; Wu, Y.; Cao, W.; Luo, K. Evaluation of Land Suitability for Construction in the Turpan–Hami Region Based on the Integration of the MaxEnt Model and Regional Planning. Land 2025, 14, 775. https://doi.org/10.3390/land14040775

AMA Style

Zhang G, Zhang L, Samat A, Wu Y, Cao W, Luo K. Evaluation of Land Suitability for Construction in the Turpan–Hami Region Based on the Integration of the MaxEnt Model and Regional Planning. Land. 2025; 14(4):775. https://doi.org/10.3390/land14040775

Chicago/Turabian Style

Zhang, Guangpeng, Li Zhang, Alim Samat, Yin Wu, Wa Cao, and Kaiyue Luo. 2025. "Evaluation of Land Suitability for Construction in the Turpan–Hami Region Based on the Integration of the MaxEnt Model and Regional Planning" Land 14, no. 4: 775. https://doi.org/10.3390/land14040775

APA Style

Zhang, G., Zhang, L., Samat, A., Wu, Y., Cao, W., & Luo, K. (2025). Evaluation of Land Suitability for Construction in the Turpan–Hami Region Based on the Integration of the MaxEnt Model and Regional Planning. Land, 14(4), 775. https://doi.org/10.3390/land14040775

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop