Next Article in Journal
Evolving Green Premiums: The Impact of Energy Efficiency on London Housing Prices over Time
Previous Article in Journal
Human–Nature Interaction Pattern Design in Landscape Architecture
 
 
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 10
10.3390/land14102052
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

Suitability Assessment of Pastoral Human Settlements in Xilingol League Based on an Optimized MaxEnt Model

by
Sen Mu
1,
Jianghong Zhen
1,2,*,
Chun Xi
1,2 and
Lei Wang
3
1
School of Geographical Sciences, Inner Mongolia Normal University, Hohhot 010022, China
2
Key Laboratory of Mongolian Plateau Climate Change and Regional Response, School of Geographical Sciences, Inner Mongolia Normal University, Hohhot 010022, China
3
College of Life and Environment Sciences, University of Birmingham, Birmingham B15 2TT, UK
*
Author to whom correspondence should be addressed.
Land 2025, 14(10), 2052; https://doi.org/10.3390/land14102052
Submission received: 15 September 2025 / Revised: 12 October 2025 / Accepted: 13 October 2025 / Published: 14 October 2025
(This article belongs to the Section Land Use, Impact Assessment and Sustainability)
Browse Figures
Versions Notes

Abstract

Assessing the suitability of human settlements is of great significance for promoting pastoral development, improving herders’ livelihoods, and advancing the construction of beautiful villages in agro-pastoral regions. Focusing on ten pastoral banners within Xilingol League, a representative pastoral region in northern China, this study employed the Google Earth Engine (GEE) platform combined with statistical datasets to evaluate settlement suitability using an optimized MaxEnt model. Fourteen key influencing factors were identified, and the spatiotemporal dynamics of settlement suitability in 2017 and 2024 were analyzed, together with predictions of suitable area distribution. The results showed that the model achieved the highest accuracy when using a linear combination of linear, quadratic, hinge, product, and threshold features with a regularization multiplier of 5.0. Suitable areas were mainly located in the southern part of the League, characterized by higher elevation, moderate temperatures, sufficient water resources, and relatively developed economies, while unsuitable areas were concentrated along the northwestern and northeastern borders with Mongolia. Spatially, settlement suitability exhibited a decreasing gradient from the southwest to the northeast. Furthermore, the dominant driving factors have gradually shifted from ecological conditions to socio-economic conditions. Overall, the suitability of pastoral human settlements in Xilingol League has continued to improve, providing new insights for suitability evaluation and spatial restructuring in pastoral regions.

1. Introduction

Rural development has become a frontier issue in geographical research and a pressing challenge in the context of China’s new urbanization and overall urban–rural development planning [1]. According to the National Bureau of Statistics of China, by the end of 2024 the national urbanization rate had reached 67%. Over the medium to long term, urbanization in China is expected to maintain a relatively moderate growth rate [2]. However, rapid urbanization has also led to rural hollowing and the outflow of rural labor [3], both of which have profoundly affected the rural environment. Scholars have projected that by 2050 China’s urbanization rate will reach 80% [4], releasing a vast amount of agricultural land. Against this backdrop of intertwined internal and external drivers, China’s rural areas are facing multiple challenges that urgently require solutions.
In light of these new trends in rural development, relevant studies should take efficient resource allocation as the starting point, establishing evaluation systems of human settlement suitability in rural areas based on the accessibility of production and living spaces. Such systems provide scientific evidence for optimizing spatial patterns [5] and for achieving optimal land use and enriching local decision-making approaches [6,7]. With ongoing urbanization, conflicts among production, living, and ecological spaces have intensified [8]. Each region possesses unique natural characteristics and economic development modes, which shape how people improve their living environments and lifestyles [9]. Thus, fostering a livable human settlement environment is not only an inevitable requirement for addressing ecological challenges but also an essential pathway for achieving sustainable development. For instance, Bojórquez-Tapia introduced a GIS-based multivariate statistical procedure for classifying land into different suitability zones [10]. In the Chinese context, scholars have explored human settlement suitability from diverse environmental perspectives, including arid oasis regions [11], plateaus [12], and major metropolitan areas [9].
In recent years, the scope of suitability evaluation has become increasingly diverse, extending beyond the field of geography. Relevant studies have been widely applied to agricultural assessment [13], underground urban space development [14], coastal land reclamation [15], elderly care land-use planning and design [16], geological analysis [17], and livestock husbandry [18]. Correspondingly, the methodological approaches have evolved from early multi-criteria evaluation (MCE) frameworks [19] toward more advanced and information-based techniques, such as accessibility analysis for production and living spaces [5], the Analytic Hierarchy Process (AHP) [20], K-means clustering and BP neural networks [17], TOPSIS [21], multiscale geographically weighted regression (MGWR) [22], geographical detectors [23], and the LSE software(1.3 version) platform [24]. At present, most studies continue to focus on traditional agricultural regions [5], mountainous areas [25], or urban agglomerations [26], where evaluation indicators are often derived from basic environmental or socioeconomic datasets [27]. However, in pastoral areas characterized by ecological fragility and sparse populations, greater attention should be given to the human perception of the environment and the comfort level of the natural setting. Therefore, it is necessary to enrich the evaluation framework from the perspectives of daily living and residential experience, so as to better capture the human–environment relationship in such regions.
The pastoral nomadic economy originated from the agropastoral systems of semi-arid desert grasslands [28], where the natural environment is currently facing severe challenges under global climate change. Since 1978, the Chinese government has implemented a series of large-scale ecological restoration projects, such as the Three-North Shelterbelt Program and the Beijing–Tianjin Sand Source Control Project. These initiatives have played a significant positive role in improving both the human living environment and regional ecological conditions [29,30], leading to a clustered spatial distribution of ecosystem services [31].
At present, a general trend in pastoral areas is the increasing proximity of livestock husbandry activities to settlements [32]. Pastoral settlements are typically characterized by a spatial pattern of “scattered and small-scale agglomeration” [33]. Although cropland has not further encroached upon pastoral living spaces [34], the degree of grassland fragmentation has intensified [35], which in turn has heightened landscape heterogeneity in pastoral regions [36]. Therefore, evaluating the habitat suitability of pastoral settlements is not only crucial for promoting sustainable development in these regions but also contributes to filling the gap in international research on settlement suitability in pastoral environments.
However, existing studies have mainly focused on urban and agricultural areas, with limited exploration of the evolution mechanisms and dynamic suitability of pastoral settlements. Moreover, few studies have employed the MaxEnt model to assess human settlement suitability in pastoral or agropastoral ecotones. Hence, this study seeks to address the following questions: (1) How has the habitat suitability of pastoral settlements evolved spatially and temporally? (2) How have the driving forces of natural, ecological, and socio-economic factors changed over time? (3) What are the policy implications of these evolutionary trends for regional planning and sustainable pastoral management?
Located in the core area of the agro-pastoral ecotone of northern China, the pastoral region of Xilingol League represents a typical pastoral area of Inner Mongolia. It plays a crucial role not only in maintaining China’s national ecological security pattern but also as an essential component of the global grassland ecosystem. At the same time, this region serves as the northern gateway of China’s Belt and Road Initiative and a key strategic corridor connecting Eurasia. Therefore, selecting this area as a case study helps to reveal the spatial evolution of human settlement suitability in Chinese pastoral regions and provides an important reference for understanding the relationship between ecological and human settlement environments in global pastoral systems. The findings also offer insights for sustainable development and spatial governance in similar regions worldwide.
Building upon previous studies on pastoral settlements in Inner Mongolia [27,37], this research develops an indicator system encompassing three dimensions—natural, ecological, and socio-economic—based on the habitat suitability theory in ecology [38,39]. Using an optimized MaxEnt model, the study evaluates the suitability of the human living environment and predicts future spatial trends of suitable areas. By integrating the results into a comprehensive evaluation framework, this study aims to elucidate the spatial-temporal evolution patterns of human settlement suitability in pastoral regions and to provide theoretical and methodological support for territorial spatial planning and spatial restructuring in these areas.

2. Materials and Methods

2.1. Study Area

Xilingol League (Figure 1) is located in central Inner Mongolia Autonomous Region, between 42°32′–46°41′ N and 111°59′–120°00′ E. The administrative area covers approximately 202,600 km2, with an average elevation above 1000 m and relatively abundant mineral resources. Grasslands dominate the landscape: meadow steppe, typical steppe, desert steppe, sandy vegetation and other grasslands together account for 87.12% of the League’s area. In 2024, the League’s gross domestic product (GDP) reached RMB 123.596 billion and the permanent resident population was 1,112,500, with an urbanization rate of 76.38%. Located within regions of both national energy security and ecological-security significance, the League has experienced marked changes in its human settlement environment driven by industrialization and urbanization; it is also characterized by frequent droughts and snow disasters, fragile ecosystems, and a relatively underdeveloped economy.
Accordingly, this study selected ten pastoral banners/cities in Xilingol League as the study area: Xilinhot City, Erenhot City, Abag Banner, Sunite Left Banner, Sunite Right Banner, Bordered Yellow Banner, Plain and Bordered White Banner, Plain Blue Banner, West Ujimqin Banner, and East Ujimqin Banner (including the Ulagai Management Area). The combined land area of these units is about 192,600 km2, accounting for 96.35% of the League’s total area. The Mongolian ethnic group constitutes the primary population. Administratively, the study area includes 10 central towns, 53 sums (towns/townships/administrative offices), and 9 state agricultural–animal husbandry farms; there are 346,900 farming and herding households and a total population of 870,500.

2.2. Data Sources and Processing

Following a review of settlement suitability studies and considering data availability, we supplemented basic datasets with a suite of indicators representing environmental suitability. The variables were grouped into three categories—natural, ecological, and socio-economic—and a total of 18 factors were compiled (Table 1). These factors included: elevation; slope (generated using the Slope tool in ArcGIS Pro 3.4); temperature–humidity index (THI); wind efficiency index (WEI); number of snowfall days; net primary productivity (NPP); normalized difference vegetation index (NDVI); wind erosion sensitivity index (WESI); desertification sensitivity index (DSI); groundwater balance (ET); distances to hospitals and schools; distance to temples; population density; GDP; livestock carrying capacity; distances to roads and railways; distance to central towns; and distance to rivers. The MaxEnt model was used to calculate each factor’s contribution, and variables with contribution rates greater than 1% were retained for subsequent analysis.
During data preparation, the Google Earth Engine (GEE) platform was fully utilized: all non-statistical remote-sensing datasets were obtained from GEE. Due to GEE data availability limits for 2024, some 2024 indicators were replaced with 2023 data. Statistical data were derived from the Xilingol League Statistical Yearbook and were spatially interpolated as needed. The vector data were obtained from the basic geographic datasets provided by the Inner Mongolia Department of Natural Resources, the National Geospatial Information Resource Catalog Service System (https://www.webmap.cn/main.do?method=index (accessed on 11 July 2025)), and Baidu Map POI data points. Distance-related raster factors were generated using the inverse distance weighting (IDW) method. Due to the lack of reliable data on future infrastructure development or settlement expansion in pastoral regions, distance-based layers were assumed to remain constant under future scenarios. High-resolution land-use data were sourced from Esri’s Sentinel-2 Land Cover Explorer (https://livingatlas.arcgis.com/landcoverexplorer/#mapCenter (accessed on 11 July 2025)) at 10 m spatial resolution; after manual visual interpretation, settlement land was extracted and converted to point data. All raster datasets were unified to the same coordinate system, raster dimensions (rows/columns), and extent, and resampled to a uniform spatial resolution of 1 km × 1 km. Finally, datasets were converted to ASCII format and stored by year for subsequent analysis.

2.3. Methods

The MaxEnt model, originally proposed by Phillips et al. as a general machine learning method, was first applied to estimate the density of species presence across landscapes [40]. With continuous methodological improvements, it has been widely adopted for modeling species distributions based on presence-only records [41] and predicting potential species ranges under current and climate change scenarios [42]. In this study, settlement points were treated as occurrence records, and an optimized MaxEnt model was employed to predict the suitability of the human settlement environment.

2.3.1. Parameter Optimization

In many studies, researchers have often relied on the default parameter settings of the MaxEnt model; however, adjusting these parameters can yield better performance [43]. In this study, ENMTools (5.26) [44] implemented in R Studio (2025.05.0 version) was applied to optimize the default MaxEnt settings. By importing settlement occurrence points and environmental factor layers with high contribution rates, a series of tuning experiments were conducted by varying the regularization multiplier to control model complexity [45]. The optimal regularization parameter obtained from these experiments was subsequently used to run the MaxEnt model.

2.3.2. Suitability Evaluation

First, ENMTools was used to determine the optimal regularization parameter. The Jackknife method was applied for variable partitioning, with 10,000 background points, a maximum of 3000 iterations, and a random seed of 2000. After model training, the best-fitting regularization parameter was identified. To avoid multicollinearity among explanatory variables, Pearson correlation analysis was employed to test inter-factor correlations.
Second, settlement data derived from land-use maps indicated 8999 settlement points in 2017 and 14,885 settlement points in 2024, with 10,000 background points. The dataset was randomly divided into training (75%) and testing (25%) subsets, while other settings were kept as default. The MaxEnt model produced outputs in ASCII format, which were subsequently used to map human settlement suitability. The Jenks natural breaks classification method was applied to divide suitability into four categories: unsuitable, low suitability, moderate suitability, and high suitability.

2.3.3. Dynamic Intensity Change and Future Suitability Prediction

Dynamic intensity change reflects the key areas of suitability transitions over a given time span and indicates the intensity of such changes. The human settlement suitability results for the two periods were processed in ArcGIS Pro using the raster calculator, with the following formula:
Y = ( X 2024 − X 2017 ) / Y e a r
where X represents the dynamic intensity, Y e a r denotes the time span, and X2017/2024 refers to the human settlement suitability results. This method illustrates whether the pastoral human settlement environment in Xilingol League has evolved toward improvement or deterioration, and clearly reveals its spatial distribution. The resulting map was classified into three categories—vulnerable areas, stable areas, and improved areas—using the natural breaks (Jenks) method, reflecting different levels of dynamic change.
In the MaxEnt model, future human settlement suitability zones can also be predicted. Based on the prediction results, the spatial distribution of various suitability categories was analyzed, and the areas of each suitability level within different banners and counties were calculated. Combined with statistical data, these results provide insights into future human settlement suitability, offering theoretical support for promoting spatial reconstruction in the pastoral areas of Xilingol League.

3. Results

3.1. Environmental Factors and Model Optimization Results

Based on the 18 environmental factors mentioned above, Pearson correlation analysis was conducted to exclude potential spatial autocorrelation among variables. The results indicated that no significant correlations existed between factors (i.e., ∣r∣ ≤ 0.8).
In the MaxEnt model, feature functions are used to characterize the relationship between species distribution and environmental variables. Common feature function combinations include five types: L (Linear), LQ (Linear + Quadratic), LQH (Linear + Quadratic + Hinge), LQHP (Linear + Quadratic + Hinge + Product), and LQHPT (Linear + Quadratic + Hinge + Product + Threshold). These combinations progressively enhance the model’s representational capacity from simple to complex. Specifically, L and LQ are suitable for describing relatively straightforward relationships; LQH can capture threshold effects of environmental variables; LQHP accounts for interactions among environmental factors; and LQHPT offers the greatest flexibility in fitting complex ecological distribution patterns. In practice, researchers typically compare model performance under different feature combinations to select the most appropriate one, thereby achieving a balance between model accuracy and interpretability.
In the MaxEnt model, five feature class combinations (L, LQ, LQH, LQHP, LQHPT) were tested (Figure 2), and the regularization multiplier (RM) was set from 1 to 5 for parameter optimization. Model tuning was performed using the ENMTools package, with the results presented in Figure 2. Overall, as RM increased, the ΔAICc values for all feature combinations gradually decreased, indicating reduced model complexity and lower risk of overfitting. Meanwhile, complex feature combinations (LQH, LQHP, LQHPT) exhibited significantly higher mean AUC values compared to simpler combinations (L, LQ).
Among them, the LQHPT combination with RM = 5 demonstrated the best performance across multiple key metrics. The mean AUC values for 2017 and 2024 reached approximately 0.845 and 0.865, respectively, representing the highest values among all combinations. The AUC difference (AUC diff) remained low in both years (<0.012), suggesting that overfitting was effectively controlled. The OR10 metric in 2024 reached a minimum of 0.1, indicating superior predictive ability compared to 2017, with relatively minor fluctuations.
Considering the minimum ΔAICc, maximum AUC, low AUC diff and OR10 values, and the absence of significant anomalies in any metric, the LQHPT + RM = 5 configuration was identified as the optimal model. This configuration balances model complexity and predictive accuracy, providing both stability and generalization capability. Therefore, LQHPT + RM = 5 was adopted in this study for human settlement suitability modeling, ensuring robust and accurate predictions.

3.2. Spatiotemporal Variation of Human Settlement Suitability

3.2.1. Influence of Environmental Factors

After eliminating multicollinearity among the influencing factors, the MaxEnt model was employed to calculate the contribution rate of each variable. Indicators with a contribution rate greater than 1% were selected and retained. The results of variable contributions were then visualized in Figure 3. In the figure, blue bars represent percent contribution, indicating the relative contribution of each environmental factor to the model output, while red bars represent permutation importance, reflecting the relative importance of each variable within the model.
In 2017, the highest percent contributions were observed for livestock carrying capacity (20.7%), ET (19.1%), and population density (17.9%). Meanwhile, NPP (25.3%), population density (22.6%), and number of snowfall days (16.7%) ranked highest in permutation importance. These results suggest that areas with high settlement suitability during this period were primarily pastoral regions with abundant water and forage resources and relatively concentrated populations.
By contrast, in 2024, the ranking of variable importance changed markedly. Population density (37.1%), GDP (15.3%), and distance to temples (9.5%) had the highest percent contributions, while population density (23.6%), NPP (14.3%), and number of snowfall days (11.4%) were dominant in permutation importance. This indicates that during this period, urban areas with concentrated populations and relatively developed economies emerged as the new human settlement suitability zones.
The temporal variation in variable importance is closely associated with socioeconomic development, adjustments in grassland utilization, and fluctuations in the climatic environment. In 2017, ecological and hydrological indicators such as “stock capacity” and the “ET” exhibited higher importance, suggesting that during the stage when grassland husbandry was predominant, ecological constraints played a decisive role in shaping settlement spatial patterns. Over time, by 2024, socioeconomic factors such as “population density” and “GDP” gained substantial importance, reflecting that under the backdrop of rapid urbanization, infrastructure expansion, and the enhancement of service functions, socioeconomic forces gradually emerged as the primary drivers of settlement distribution. Meanwhile, the relative decline in the importance of natural factors indicates that human activities have, to some extent, alleviated or substituted the dependence on environmental conditions. Consequently, the determinants of settlement suitability have shifted from ecological–resource constraints to socioeconomic drivers, highlighting a transformation from environmental determinism toward socioeconomic dominance in the evolution of pastoral settlements. This transition not only reflects the coupled interactions between natural and human systems but also underscores the profound influence of regional development policies and economic restructuring on the spatial evolution of settlements. These changes also illustrate the spatial transition of suitable human settlement areas from pastoral regions to cities and towns.

3.2.2. Spatiotemporal Variation of Human Settlement Suitability Zones

Based on the MaxEnt output, human settlement suitability was classified into four categories using the natural breaks method. Reclassification tools were then applied to calculate the areal changes of different suitability zones (Table 2). In terms of area, unsuitable zones decreased by 2.67%, while suitable, moderately suitable, and highly suitable zones all expanded, with moderately suitable zones showing the smallest increase (0.55%). These results indicate that the overall human settlement environment in the Xilingol League pastoral area improved during the study period. The increase in construction land did not come at the expense of environmental quality, suggesting a continuous enhancement of human settlement conditions.
From a spatiotemporal perspective (Figure 4), several patterns are evident. First, highly suitable and moderately suitable zones were mainly concentrated in the southern regions, particularly in Plain and Bordered White Banner, Plain Blue Banner, and Bordered Yellow Banner, where suitable and moderately suitable zones were interlaced. The scattered unsuitable patches in Plain and Bordered White Banner and Plain Blue Banner largely disappeared by 2024. In Xilinhot City and its southern surroundings, as well as in Sonid Left Banner, Sonid Right Banner, and southern Abaga Banner, moderately suitable zones were observed; by 2024, some of these areas in Abaga Banner experienced transitions between suitable and moderately suitable classes. In West Ujimqin Banner, moderately suitable zones formed a cross-shaped network pattern. Unsuitable zones displayed notable spatiotemporal dynamics, generally retreating from central areas toward the periphery. For instance, unsuitable zones in Sonid Left Banner, Sonid Right Banner, and Abaga Banner contracted toward the northern border with Mongolia. In Sonid Left Banner and central Abaga Banner, large portions of unsuitable zones were converted into suitable zones, while in northern Sonid Right Banner, unsuitable zones expanded eastward. In East and West Ujimqin Banners, unsuitable zones decreased in a scattered pattern. Overall, the changes reveal a contraction of unsuitable zones toward the northern border and a transformation of suitable zones from fragmented to contiguous patches, with both improvements and localized deteriorations in suitability.
In terms of dynamic suitability intensity (Figure 5a), the overall trend in the Xilingol League pastoral area was one of improvement, with stable zones dominating the landscape, accompanied by both enhancement and fragile zones. Notably, improvements were evident along approximately 45° N, especially in Xilinhot City, Sonid Right Banner, and Abaga Banner. Scattered improvement patches also emerged at the eastern boundary between East and West Ujimqin Banners. While most of the region showed a persistent trend toward improved settlement suitability, certain areas exhibited degradation, forming fragile zones that coexisted spatially with stable and improvement zones. These fragile areas often appeared in scattered patterns and overlapped with enhancement zones. This indicates that although the settlement environment in the Xilingol League pastoral area is steadily improving, its ecological conditions remain vulnerable. Therefore, special attention should be given to the risk of degradation in ecologically fragile zones during the process of settlement quality enhancement.

3.3. Prediction of Future Human Settlement Suitability Zones

Figure 5b illustrates the spatial distribution of future human settlement suitability zones in the pastoral areas of Xilingol League. Compared with the suitability conditions in 2024, the total area of suitable zones is projected to expand. Spatially, the highly suitable and moderately suitable zones are mainly concentrated in the southern part of the region, including the Plain Blue Banner, the Bordered Yellow Banner, and the Plain and Bordered White Banner. Moderate-scale suitable zones are also distributed in Sonid Right Banner, Abag Banner, and the central and southern areas of Xilinhot City, while in West Ujimqin Banner, the highly suitable and moderately suitable zones display a cross-axis pattern within the banner territory.
The generally suitable zones tend to expand northward, gradually compressing the extent of unsuitable zones toward the northeast and northwest, although some unsuitable areas still remain in the central part of the study area. According to the area statistics of predicted changes (Table 3), the overall trend is stable yet improving. Given the relatively poor baseline of human settlement suitability in the northeast and northwest, these areas show greater potential for improvement. Newly added suitable zones are mainly concentrated in East Ujimqin Banner, Sonid Right Banner, and West Ujimqin Banner. However, because of their large base of unsuitable areas, the path toward substantial improvement in human settlement conditions remains challenging.
Overall, the southeastern and southern parts of the study area are projected to become the most suitable human settlement zones in the future, while the northeastern and northwestern regions are likely to remain the least suitable.

4. Discussion

The study area selected in this paper is the pastoral region of Xilingol League, which serves as the primary environmental carrier for pastoralism and herders, and features diverse natural landscapes such as mountains, grasslands, and deserts [46]. Its ecological environment is relatively fragile, with complex geomorphological conditions, substantial natural heterogeneity, pronounced and intense environmental changes, and significant climatic variability. It is highly sensitive to climate change and faces ecological crises such as grassland desertification. Over the past two decades, with the Chinese government actively promoting ecological restoration projects, the ecological environment of the Xilingol pastoral region has significantly improved. The results reveal that suitable zones are primarily distributed in the southern part of the League, characterized by moderate temperatures, relatively abundant precipitation, concentrated populations, and comparatively advanced economic development. Overall suitability decreases from southeast to northwest, which is consistent with previous research findings [11,47].
The increasing importance of population density indicates greater concentration of urban scale and urban populations, while rural settlements in pastoral areas tend to be more evenly distributed [37]. GDP reflects the level of regional economic development, as industry and services absorb a larger labor force, and higher income levels enhance the attractiveness of labor inflows. Compared with agricultural zones, pastoral regions are less favorable for farming due to climatic constraints, and herders without large-scale fixed arable land often prefer areas close to water sources, with mild climates, abundant precipitation, and higher vegetation coverage for production and living activities [28]. Central towns benefit from superior infrastructure and social resources, such as hospitals, schools, temples, and transport networks, whose importance remains relatively stable [48]. The growing importance of distance to roads highlights the increasingly close population, material, and economic linkages between pastoral areas and towns [49].
Assessing interregional human settlement suitability requires integrating multiple influencing factors. The interplay of geomorphology, hydrology, and climate leads to differentiated spatial patterns of suitability [12]. Compared with agricultural zones, the pastoral regions exhibit no obvious tendency of suitable zones being concentrated at lower altitudes [27]; instead, suitability is primarily observed in the southern high-altitude areas. Under the siphon effect of the Beijing–Tianjin–Hebei and Hohhot–Baotou–Ordos urban agglomerations, population and goods are increasingly drawn toward large cities, thereby widening the urban–rural gap and accelerating urbanization. Therefore, the findings of this study have practical implications for spatial planning in pastoral areas. In terms of spatial patterns, priority should be given to the protection and optimization of highly suitable areas located in the southern regions and zones with convenient transportation, while ensuring a rational functional layout between towns and pastoral settlements. Regarding the urban–rural structure, it is essential to strengthen the complementary linkages between towns and pastoral villages, thereby promoting a networked spatial pattern characterized by central towns serving as cores and surrounding pastoral villages developing in a coordinated manner.
The MaxEnt model has been widely applied in predicting species distributions, but non-optimized models may produce biased predictions [50]. The default parameterization of MaxEnt originates from early developer tests on species data. With the expansion of its application to diverse geographic contexts, it is necessary to adapt the model for predicting potential distributions across different regions [41]. Adjusting the regularization multiplier is essential to control overfitting, as increasing model complexity can negatively affect prediction accuracy [45]. The MaxEnt model also has certain limitations. Its results are highly dependent on the selection of input variables and parameter settings, and the model’s feasibility may be affected when data availability is limited. Furthermore, as MaxEnt primarily establishes correlative relationships between probability distributions and environmental variables, its explanatory power regarding socioeconomic or institutional factors remains limited—this may partly explain its limited application in pastoral studies. To mitigate these issues, this study employed ENMTools to optimize the MaxEnt model’s regularization multiplier and feature class combinations. ENMTools provides comparable optimization and evaluation functions to ENMeval, including AICc-based model selection and overfitting control, while also offering additional capabilities such as niche overlap and variable importance analyses. These features make ENMTools particularly suitable for the multidimensional ecological and socioeconomic context of pastoral regions. Multiple parameter combinations were tested, and the configuration with the lowest complexity and highest predictive performance was selected. This approach ensured that the model remained both parsimonious and accurate, thereby enhancing the reliability and robustness of the prediction results.
Moreover, human settlement suitability must also take into account the specific conditions of ethnic minority regions. Agro-pastoral ecosystems have unique land-use demands and localized governance structures. The challenges of sparse population density, ethnic and religious diversity, and uneven development require careful attention [51]. Narrowing the urban–rural infrastructure gap, addressing the development needs of pastoral regions, and reducing income disparities between urban and rural residents are essential [52]. In addition, broad participation should be encouraged by engaging social groups, market actors, and grassroots practitioners in the design and implementation of human settlement strategies [51]. Specifically, future efforts to enhance the human settlement environment in pastoral regions can be advanced through the following approaches. First, at the spatial planning level, development zones, restriction zones, and conservation zones should be delineated in accordance with the spatial pattern of suitability, so as to prevent ecological degradation caused by uncontrolled expansion. Second, regarding urban–rural spatial structure, public services should be extended to pastoral villages, while transportation and information networks should be improved to narrow the urban–rural development gap. Third, in terms of industrial development, the focus should be placed on promoting diversified industries such as characteristic animal husbandry, ecotourism, and renewable energy, thereby achieving multi-dimensional economic growth. Fourth, from the perspective of social governance, it is essential to address the social needs and cultural identities of ethnic minority communities, strengthen grassroots participation and community co-governance, and enhance the long-term sustainability of human settlement development in pastoral areas.
It is worth noting that current research on the suitability of human settlements in pastoral areas remains limited, particularly with respect to studies that integrate natural, ecological, and socioeconomic dimensions in a comprehensive analytical framework. Existing international research has predominantly focused on urban expansion and land-use change, while paying insufficient attention to the human settlement environments of ecologically fragile regions such as grassland pastoral areas. Therefore, this study not only fills a critical gap in the evaluation of human settlement suitability within pastoral regions but also provides valuable insights for settlement planning in comparable global contexts, including Central Asia, Mongolia, and the African grassland zones.

5. Conclusions

Compared with existing studies that primarily focus on agricultural or urban areas, this study integrates natural, ecological, and socioeconomic dimensions based on Google Earth Engine (GEE) and statistical data. By applying an optimized MaxEnt model, we evaluated the human settlement suitability of pastoral areas in Xilingol League, identified the contribution and relative importance of influencing factors, and proposed a suitability assessment framework that better reflects the characteristics of pastoral regions. This framework not only provides empirical evidence for the sustainable development of China’s pastoral areas but also offers new perspectives and methodological references for human–environment studies in ecologically fragile regions worldwide.
The results indicate a continuous improvement in the human settlement environment of Xilingol League from 2017 to 2024, with the areas classified as “most suitable area” and “more suitable area” increasing by 0.59% and 0.55%, respectively. Spatially, settlement suitability displays a declining gradient from southwest to northeast, forming a heterogeneous pattern in which improvement and degradation coexist. Notably, the enhancement of suitability is more pronounced in areas previously categorized as “unsuitable area”.
The temporal comparison of variable importance further reveals a transformation in dominant driving mechanisms—from ecological and hydrological constraints in 2017 to socioeconomic drivers in 2024. Population density and GDP have become the principal forces promoting the improvement of settlement suitability, reflecting the growing influence of urbanization, infrastructure expansion, and service enhancement. In contrast, the relative importance of natural and ecological indicators has declined, indicating that human activities have progressively mitigated the constraints imposed by environmental conditions. Consequently, the determinants of settlement suitability have shifted from ecological–resource constraints toward socioeconomic dynamics, underscoring a transition from environmental determinism to socioeconomic dominance.

Author Contributions

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

Funding

The author declares that the research, writing and/or publication of this article have been funded. This research was supported by the National Natural Science Foundation of China (Grant No. 42361029) and the Natural Science Foundation of Inner Mongolia (Grant No. 2025LHMS04008).

Data Availability Statement

The original contributions presented in this study are included in the article. Further inquiries can be directed to the corresponding author.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Wang, C.; Guo, J.; Liu, C.; Peng, Y.; Tang, Y. Research Status, Hotspots, and Trend Analysis of the Rural Living Environment Upgrade in China from 1992 to 2022: A Bibliometric and Narrative Review Analysis. Sustainability 2023, 15, 10508. [Google Scholar] [CrossRef]
  2. Liang, L.; Chen, M.; Lu, D. Revisiting the relationship between urbanization and economic development in China since the reform and opening-up. Chin. Geogr. Sci. 2022, 32, 1–15. [Google Scholar] [CrossRef]
  3. Huang, Q.; Song, W.; Song, C. Consolidating the Layout of Rural Settlements Using System Dynamics and the Multi-Agent System. J. Clean. Prod. 2020, 274, 123150. [Google Scholar] [CrossRef]
  4. Wang, S.; Bai, X.; Zhang, X.; Reis, S.; Chen, D.; Xu, J.; Gu, B. Urbanization Can Benefit Agricultural Production with Large-Scale Farming in China. Nat. Food 2021, 2, 183–191. [Google Scholar] [CrossRef] [PubMed]
  5. Liu, Y.; Ye, Q.; Li, J.; Kong, X.; Jiao, L. Suitability evaluation of rural settlements based on accessibility of production and living: A case study of Tingzu Town in Hubei province of China. Chin. Geogr. Sci. 2016, 26, 550–565. [Google Scholar] [CrossRef]
  6. Xu, Z.; Zhou, S.; Zhang, C.; Yang, M.; Jiang, M. A Bayesian network model for suitability evaluation of underground space development in urban areas: The case of Changsha, China. J. Clean. Prod. 2023, 418, 138135. [Google Scholar] [CrossRef]
  7. Zhou, C.; He, L.; He, J.; Zhang, Y.; Soh, C.K. Suitability evaluation of underground space development based on Bayesian network model: A case study considering population evacuation, excavation safety, and spatial connectivity. Expert Syst. Appl. 2025, 291, 128399. [Google Scholar] [CrossRef]
  8. Zhu, Z.; Peng, S.; Ma, X.; Lin, Z.; Ma, D.; Shi, S.; Gong, L.; Huang, B. Identification of potential conflicts in the production-living-ecological spaces of the Central Yunnan Urban Agglomeration from a multi-scale perspective. Ecol. Indic. 2024, 165, 112206. [Google Scholar] [CrossRef]
  9. Xu, Y.; Sun, J.; Zhang, J.; Xu, Y.; Zhang, M.; Liao, X. Combining AHP with GIS in synthetic evaluation of environmental suitability for living in China’s 35 major cities. Int. J. Geogr. Inf. Sci. 2012, 26, 1603–1623. [Google Scholar] [CrossRef]
  10. Bojórquez-Tapia, L.A.; Díaz-Mondragón, S.; Ezcurra, E. GIS-based approach for participatory decision making and land suitability assessment. Int. J. Geogr. Inf. Sci. 2001, 15, 129–151. [Google Scholar] [CrossRef]
  11. Halik, W.; Mamat, A.; Dang, J.H.; Deng, B.S.; Tiyip, T. Suitability analysis of human settlement environment within the Tarim Basin in Northwestern China. Quat. Int. 2013, 311, 175–180. [Google Scholar] [CrossRef]
  12. Feng, W.; Lu, H.; Xiang, M. Evaluation of the natural suitability of human settlements in the western Sichuan plateau region of China. Sci. Rep. 2025, 15, 1552. [Google Scholar] [CrossRef]
  13. Geng, S.; Shi, P.; Zong, N.; Zhu, W. Agricultural land suitability of production space in the Taihang Mountains, China. Chin. Geogr. Sci. 2019, 29, 1024–1038. [Google Scholar] [CrossRef]
  14. Dou, F.; Li, X.; Xing, H.; Yuan, F.; Ge, W. 3D geological suitability evaluation for urban underground space development-a case study of Qianjiang Newtown in Hangzhou, Eastern China. Tunn. Undergr. Space Technol. 2021, 115, 104052. [Google Scholar] [CrossRef]
  15. Feng, L.; Zhu, X.; Sun, X. Assessing coastal reclamation suitability based on a fuzzy-AHP comprehensive evaluation framework: A case study of Lianyungang, China. Mar. Pollut. Bull. 2014, 89, 102–111. [Google Scholar] [CrossRef]
  16. Yang, J.; Lou, Z.; Tang, X.; Sun, Y. Multi-Source Data-Based Evaluation of Suitability of Land for Elderly Care and Layout Optimization: A Case Study of Changsha, China. Sustainability 2023, 15, 2034. [Google Scholar] [CrossRef]
  17. 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] [CrossRef]
  18. Qiu, L.; Zhu, J.; Pan, Y.; Hu, W.; Amable, G.S. Multi-Criteria Land Use Suitability Analysis for Livestock Development Planning in Hangzhou Metropolitan Area, China. J. Clean. Prod. 2017, 161, 1011–1019. [Google Scholar] [CrossRef]
  19. Dai, L.; Zhao, X.; He, H.S.; Deng, H.; Yu, D.; Zhou, L.; Wu, S. Evaluating Land-Use Suitability of an Industrial City in Northeast China. Int. J. Sustain. Dev. World Ecol. 2008, 15, 378–382. [Google Scholar] [CrossRef]
  20. Ye, W.; Huang, J.; Xu, P.; Yuan, J.; Zeng, L.; Zhang, Y.; Wang, Y.; Wang, S.; Xu, X.; Guo, Z.; et al. Suitability Evaluation of Underground Space Development by Considering Socio-Economic Factors—An Empirical Study from Longgang Region of China. Sustainability 2025, 17, 2788. [Google Scholar] [CrossRef]
  21. Liu, Y.; Cui, J.; Kong, X.; Zeng, C. Assessing suitability of rural settlements using an improved technique for order preference by similarity to ideal solution. Chin. Geogr. Sci. 2016, 26, 638–655. [Google Scholar] [CrossRef]
  22. Chen, L.; Zhong, Q.; Li, Z. Analysis of spatial characteristics and influence mechanism of human settlement suitability in traditional villages based on multi-scale geographically weighted regression model: A case study of Hunan province. Ecol. Indic. 2023, 154, 110828. [Google Scholar] [CrossRef]
  23. Wang, H.; Qin, F.; Xu, C.; Li, B.; Guo, L.; Wang, Z. Evaluating the Suitability of Urban Development Land with a Geodetector. Ecol. Indic. 2021, 123, 107339. [Google Scholar] [CrossRef]
  24. Nguyen, H.; Nguyen, T.; Hoang, N.; Bui, D.; Vu, H.; Van, T. The Application of LSE Software: A New Approach for Land Suitability Evaluation in Agriculture. Comput. Electron. Agric. 2020, 173, 105440. [Google Scholar] [CrossRef]
  25. Mao, R.; Xiao, J.; Ren, P. Spatiotemporal Evolution and Suitability Evaluation of Rural Settlements in the Typical Mountainous Area of the Upper Minjiang River: A Case Study of Lixian County, Sichuan Province, China. Sustainability 2025, 17, 2902. [Google Scholar] [CrossRef]
  26. Ma, Y.; Xue, F.; Yang, Z. Coupling study on territory space suitability evaluation and construction land expansion simulation: A case study of Jiangxi province, China. Environ. Dev. Sustain. 2023, 25, 8279–8298. [Google Scholar] [CrossRef]
  27. 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]
  28. Wang, J.; Deng, C.; Wan, X. Reconsideration of the origins of the pastoral nomadic economy in the Eurasian Steppe. Sci. China-Earth Sci. 2022, 65, 2057–2067. [Google Scholar] [CrossRef]
  29. Huang, J.; Zhang, Q.; Tan, J.; Yue, D.; Ge, Q. Association between Forestry Ecological Engineering and Dust Weather in Inner Mongolia: A Panel Study. Phys. Chem. Earth 2018, 104, 76–83. [Google Scholar] [CrossRef]
  30. Xu, Y.; Zhou, G.; Zhou, L.; He, X.; Tian, Z. How Does the Three-North Shelterbelt Engineering of China Improve Its Habitat Quality? A Study of 40 Years of Change Tracking and Driving Factors. Land Degrad. Dev. 2025, 36, 408–423. [Google Scholar] [CrossRef]
  31. Shao, Y.; Liu, Y.; Ma, T.; Sun, L.; Yang, X.; Li, X.; Wang, A.; Wang, Z. Conservation Effectiveness Assessment of the Three Northern Protection Forest Project Area. Forests 2023, 14, 2121. [Google Scholar] [CrossRef]
  32. Zhang, H.; Chen, W.; Liu, W.; Liu, Z.; Liu, H. The evolution of settlement system and the paths of rural revitalization in alpine pastoral areas of the Qinghai-Tibet plateau: A case study of Nagqu County. Ecol. Indic. 2023, 150, 110274. [Google Scholar] [CrossRef]
  33. Zhang, L.; Zhao, T.; Rong, L. Construction of public service facilities layout network in pastoral areas based on psychological cognition range information—A case study of inner Mongolia pastoral areas of East Wuzhumuqin Banner in Xilingol. Eur. J. Remote Sens. 2020, 53, 114–125. [Google Scholar] [CrossRef]
  34. Wuyun, D.; Sun, L.; Chen, Z.; Hou, A.; Crusiol, L.G.T.; Yu, L.; Chen, R.; Sun, Z. The Spatiotemporal Change of Cropland and Its Impact on Vegetation Dynamics in the Farming-Pastoral Ecotone of Northern China. Sci. Total Environ. 2022, 805, 150286. [Google Scholar] [CrossRef]
  35. Wu, J.; Han, P.; Yu, J.; Jarvie, S.; Zhang, Y.; Zhang, Q. Edge Grassland Provide a Stronger Thermal Buffer against Core Grassland in the Agro-Pastoral Ecotone of Inner Mongolia. Ecol. Indic. 2023, 154, 110762. [Google Scholar] [CrossRef]
  36. Shi, F.; Liu, S.; Sun, Y.; An, Y.; Zhao, S.; Liu, Y.; Li, M. Ecological network construction of the heterogeneous agro-pastoral areas in the upper Yellow River Basin. Agric. Ecosyst. Environ. 2020, 302, 107069. [Google Scholar] [CrossRef]
  37. Peng, Y.; Wang, Q. Spatial distribution and influencing factors of settlements in the farming-pastoral ecotone of Inner Mongolia, China. Ecosyst. Health Sustain. 2020, 6, 1771213. [Google Scholar] [CrossRef]
  38. Halvorsen, R.; Mazzoni, S.; Bryn, A.; Bakkestuen, V. Opportunities for Improved Distribution Modelling Practice via a Strict Maximum Likelihood Interpretation of MaxEnt. Ecography 2015, 38, 172–183. [Google Scholar] [CrossRef]
  39. Guillera-Arroita, G.; Lahoz-Monfort, J.J.; Elith, J. Maxent Is Not a Presence-Absence Method: A Comment on Thibaud et al. Methods Ecol. Evol. 2014, 5, 1192–1197. [Google Scholar] [CrossRef]
  40. Phillips, S.J.; Anderson, R.P.; Schapire, R.E. Maximum Entropy Modeling of Species Geographic Distributions. Ecol. Model. 2006, 190, 231–259. [Google Scholar] [CrossRef]
  41. Elith, J.; Phillips, S.J.; Hastie, T.; Dudík, M.; Chee, Y.E.; Yates, C.J. A Statistical Explanation of MaxEnt for Ecologists: Statistical Explanation of MaxEnt. Divers. Distrib. 2011, 17, 43–57. [Google Scholar] [CrossRef]
  42. Elith, J.; Kearney, M.; Phillips, S. The art of modelling range-shifting species. Methods Ecol. Evol. 2010, 1, 330–342. [Google Scholar] [CrossRef]
  43. Merow, C.; Smith, M.J.; Silander, J.A. 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] [CrossRef]
  44. Warren, D.L.; Glor, R.E.; Turelli, M. ENMTools: A Toolbox for Comparative Studies of Environmental Niche Models. Ecography 2010, 33, 607–611. [Google Scholar] [CrossRef]
  45. Radosavljevic, A.; Anderson, R.P. Making better MAXENT models of species distributions: Complexity, overfitting and evaluation. J. Biogeogr. 2014, 41, 629–643. [Google Scholar] [CrossRef]
  46. Liu, X.; Zhu, Z.; Liu, X.; Yu, M. Thresholds of key disaster-inducing factors and drought simulation in the Xilinguole Grassland. Ecol. Inform. 2021, 64, 101380. [Google Scholar] [CrossRef]
  47. Feng, Z.; Yang, Y.; Zhang, D.; Tang, Y. Natural environment suitability for human settlements in China based on GIS. J. Geogr. Sci. 2009, 19, 437–446. [Google Scholar] [CrossRef]
  48. Du, F.; Liu, Z.; Oniki, S. Factors Affecting Herdsmen’s Grassland Transfer in Inner Mongolia, China. Jpn. Agric. Res. Q. JARQ 2017, 51, 259–269. [Google Scholar] [CrossRef]
  49. Zhou, H.; Wang, C.; Bai, Y.; Ning, X.; Zang, S. Spatial and Temporal Distribution of Rural Settlements and Influencing Mechanisms in Inner Mongolia, China. PLoS ONE 2022, 17, e0277558. [Google Scholar] [CrossRef] [PubMed]
  50. Kong, W.-Y.; Li, X.H.; Zou, H.F. Optimizing MaxEnt model in the prediction of species distribution. Chin. J. Appl. Ecol. 2019, 30, 2116–2128. [Google Scholar] [CrossRef]
  51. Cheng, Z.; Tang, A.; Cai, J.; Song, T. Exploring the high-quality county-level development and governance response for farming-pastoral ecotone in China: A case study of Kulun. Agriculture 2022, 12, 2042. [Google Scholar] [CrossRef]
  52. Li, W.; Huntsinger, L. China’s Grassland Contract Policy and Its Impacts on Herder Ability to Benefit in Inner Mongolia: Tragic Feedbacks. Ecol. Soc. 2011, 16, 1. [Google Scholar] [CrossRef]
Land 14 02052 g001
Figure 1. Geographic overview of the pastoral areas in Xilingol League.
Figure 1. Geographic overview of the pastoral areas in Xilingol League.
Land 14 02052 g001
Land 14 02052 g002
Figure 2. Model performance under different parameters and feature class combinations.
Figure 2. Model performance under different parameters and feature class combinations.
Land 14 02052 g002
Land 14 02052 g003
Figure 3. Relative contributions of environmental factors for each year.
Figure 3. Relative contributions of environmental factors for each year.
Land 14 02052 g003
Land 14 02052 g004
Figure 4. Spatiotemporal patterns of settlement suitability zones. (a) 2017, (b) 2024.
Figure 4. Spatiotemporal patterns of settlement suitability zones. (a) 2017, (b) 2024.
Land 14 02052 g004
Land 14 02052 g005
Figure 5. Dynamic intensity of settlement suitability changes and predicted future distribution. (a) dynamic changes in suitability zones, (b) predicted suitability distribution.
Figure 5. Dynamic intensity of settlement suitability changes and predicted future distribution. (a) dynamic changes in suitability zones, (b) predicted suitability distribution.
Land 14 02052 g005
Table 1. Environmental indicators and their data sources.
Table 1. Environmental indicators and their data sources.
TypeFactorSourceYear
Natural factorDEMhttps://www.gscloud.cn/2024
Slope
THIhttps://earthengine.google.com/2017/2023
WEI2017/2023
Snowfall days2017/2024
Ecological factorNDVIGEE (https://earthengine.google.com/)2017/2024
DSI2017/2024
WESI2017/2024
NPP2017/2024
ET2017/2023
Social factorGDPStatistical Yearbook of Xilingol League2017/2023
Density of Pop2017/2023
Dist to river
Stock capacityStatistical Yearbook of Xilingol League2017/2023
Dist to town
Dist to school and hospitalhttps://map.baidu.com/2017/2024
Dist to temple
Dist to railway and road
Table 2. Area statistics of human settlement suitability categories.
Table 2. Area statistics of human settlement suitability categories.
CategoriesYearArea (Km2)Percent (%)YearArea (Km2)Percent (%)
Unsuitable area201784,501.3843.88%202479,365.4541.21%
Suitable area66,825.434.70%69,778.336.23%
More suitable area24,578.3512.76%25,638.413.31%
Most suitable area16,676.078.66%17,799.059.25%
Table 3. Area statistics of newly added human settlement suitability zones.
Table 3. Area statistics of newly added human settlement suitability zones.
AreaUnchanged Area (Km2)New More
Suitable Area (Km2)		New Most
Suitable Area (Km2)
Erlianhot84.9187.400.00
Xilinhot12,478.632352.394.99
Abaga Banner24,278.133348.787.49
Sonid Left Banner27,180.236344.2016.23
Sonid Right Banner18,591.847671.4754.94
East Ujimqin County40,201.575533.8576.17
West Ujimqin Banner17,535.515049.3939.96
Bordered Yellow Banner4315.20820.340.00
Plain And Bordered White Banner6226.8341.200.00
Plain Blue Banner9544.39686.741.25
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

Mu, S.; Zhen, J.; Xi, C.; Wang, L. Suitability Assessment of Pastoral Human Settlements in Xilingol League Based on an Optimized MaxEnt Model. Land 2025, 14, 2052. https://doi.org/10.3390/land14102052

AMA Style

Mu S, Zhen J, Xi C, Wang L. Suitability Assessment of Pastoral Human Settlements in Xilingol League Based on an Optimized MaxEnt Model. Land. 2025; 14(10):2052. https://doi.org/10.3390/land14102052

Chicago/Turabian Style

Mu, Sen, Jianghong Zhen, Chun Xi, and Lei Wang. 2025. "Suitability Assessment of Pastoral Human Settlements in Xilingol League Based on an Optimized MaxEnt Model" Land 14, no. 10: 2052. https://doi.org/10.3390/land14102052

APA Style

Mu, S., Zhen, J., Xi, C., & Wang, L. (2025). Suitability Assessment of Pastoral Human Settlements in Xilingol League Based on an Optimized MaxEnt Model. Land, 14(10), 2052. https://doi.org/10.3390/land14102052

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