Balancing social development and ecological conservation: a case study from Shaanxi, China on future ecosystem service optimization

Abstract

Clarifying the influence of land-use transitions on ecosystem services (ESs) is essential for regional sustainability. Focusing on Shaanxi Province, this study develops an integrated framework that couples the LightGBM-PLUS model for land-use simulation with the InVEST model for quantitative ESs assessment, further incorporating ecological security patterns (ESP) and grey multi-objective optimization (GMOP) to optimize ES outcomes. The coupled LightGBM-PLUS model demonstrates high reliability (93% Overall Accuracy; Kappa 0.90). Scenario analysis reveals distinct trade-offs: the Natural Development (ND) and Economic Priority (EP) scenarios lead to limited ESs improvements and substantial ESs losses, respectively, while the Ecological Land Protection (ELP) scenario enhances ecological functions but constrains economic growth. The Coordinated Development scenario—enabled by the integration of ESP and GMOP—simultaneously improves water yield, soil conservation, carbon storage, and habitat quality, achieving a balanced ecological–economic pathway. Natural factors such as topography and climate are the dominant drivers of ESs variations, supplemented by socioeconomic influences. Overall, this study provides a systematic approach to linking land-use transitions with ESs optimization, offering practical guidance for sustainable regional planning.

1 Introduction

Ecosystem Services (ESs) refer to the functions and services provided by natural ecosystems on Earth’s surface that contribute to human well-being, encompassing various economic and social values (Fang et al., 2021). Ecosystem services (ESs) are crucial for human survival and development, encompassing provisioning (e.g., food, water), regulating (e.g., purification, climate regulation), cultural (e.g., aesthetic value), and supporting services (e.g., soil conservation, biodiversity). Together, they sustain life and development on Earth (Hasan et al., 2020). Over the past century, and especially following the Third Industrial Revolution, rapid population growth and technological advancement have accelerated urbanization. Since the 21st century, the intensification of human-environment conflicts and rapid economic development have posed significant threats to the health and stability of ecosystems (Liu C. et al., 2022). Global ecological crises—including climate change, biodiversity loss, land degradation, and water scarcity—have drawn increasing attention to ESs (Castillón et al., 2025). Since the last century, land use/cover change (LUCC) has been a major driver of ES dynamics (Sheng and Huang, 2025), as urbanization, agricultural expansion, and deforestation exert substantial impacts on ecosystem structure and function. As a direct representation of human activities, LUCC profoundly reshapes the quality and spatial distribution of ESs (Cabernard et al., 2024). Moreover, land-use transitions can alter pathways for microbial and viral transport in soils and groundwater, which has been increasingly recognized as a key component of ecosystem stability (Jat Baloch et al., 2026). Global initiatives such as GLP, TEEB, and IPBES—focusing on biodiversity and ESs—have further provided extensive theoretical and empirical foundations for advancing LUCC–ESs research (Liu et al., 2020).

Within the framework of sustainable development, understanding and quantifying ESs is crucial for achieving a balance between economic growth, social progress, and environmental protection (Li F. et al., 2023). In response to the urgent global demand for sustainable development, the World Bank introduced the concept of Nature-based Solutions (NbS) in 2008. At its core, NbS emphasizes the strategic selection, conservation, and management of critical locations and ecosystems (Liu Y. et al., 2022). Drawing inspiration from NbS principles, this study focuses on four ESs: Water Yield (WY), Soil Conservation (SC), Carbon Storage (CS), and Habitat Quality (HQ). WY directly impacts water resource availability (Li M. et al., 2022), while SC plays a critical role in maintaining soil fertility and preventing erosion (Eekhout and de Vente, 2022). CS reflects an ecosystem’s capacity for carbon sequestration (Fu and Xu, 2023), and HQ is fundamental for biodiversity, ecological balance, and ecosystem stability (Yang, 2021). These four ESs collectively form a Water-Soil-Carbon-Habitat (WSCH) ESs framework, which is vital for human well-being and the advancement of sustainable development.

The Ecological Security Pattern (ESP), as a critical theoretical framework for spatial optimization, has gradually become a key pillar for land-use optimization research. Existing studies mostly achieve different development pathways by adjusting model parameters or restricting land-use targets (Nie et al., 2023). While some studies have incorporated areas of critical ESs or ecological redline zones as ecological constraints (Huang et al., 2019; Zhang et al., 2023), they often adopt a singular perspective focused solely on ecological conservation, lacking a comprehensive consideration of the practical needs of urban development. Against the backdrop of China’s new urbanization and urban–rural integration development goals, as well as the ongoing urbanization process (Qu et al., 2025), this study proposes a more holistic approach. By introducing an evaluation system that combines Urban Development Suitability (UDS) and Ecological Protection Importance (EPI), it seeks to strike a balance between ecological conservation and urban development. Additionally, the study integrates ecological sources and corridors to construct a complete ESP (Kang et al., 2021). This ESP framework not only effectively safeguards ecologically sensitive areas but also reasonably accommodates urban development needs, thus contributing to the sustainable development goal of achieving harmony between humans and nature.

By coupling multiple models, this study constructs various land-use scenarios to explore the impacts of different land-use strategies on spatial patterns and ESs. The mainstream land-use simulation models include CA-Markov, CLUE-S, and Geo-FLUS (Wang et al., 2023). Among these, the CA-Markov model estimates future land use based on historical data, making it widely adopted due to its simplicity and the accessibility of required data (Aniah et al., 2023). The CLUE-S model excels in analyzing land use and LUCC at finer scales (Liao et al., 2022), while Geo-FLUS integrates system dynamics (SD) with cellular automata (CA), offering a hybrid approach (Zhang and Li, 2022). However, these models often struggle to accurately capture the nonlinear drivers behind LUCC (Shi et al., 2023). The Patch-generating Land Use Simulation (PLUS) model, a comprehensive framework integrating multiple sub-models, introduces a novel approach to land use simulation (Liang et al., 2021). By incorporating a Land Expansion Analysis Strategy (LEAS) and a random forest-based rule-mining framework, PLUS enables finer simulations of land-use patch dynamics and an in-depth analysis of potential LUCC drivers (Wang et al., 2023). Considering data scale, reproducibility, and accuracy requirements, this study employs the PLUS model to construct multiple scenarios representing different development pathways. Existing integrations of ESP and PLUS have mainly focused on establishing ecological constraints (Luo et al., 2025), yet they often lack land-use allocation and corridor constraints derived from future development needs. Moreover, few frameworks simultaneously optimize ecosystem service outcomes and socioeconomic objectives at the provincial scale, leaving comprehensive and operational optimization approaches limited. In this study, the multi-objective programming (MOP) model enables flexible adjustment of model inputs, objective functions, and constraints according to specific requirements. When combined with the PLUS model, it provides a more adaptable approach suited to diverse research aims and decision-making contexts (Li C. et al., 2023).

The Chinese government outlined its vision for 2035 in the “Long-Range Objectives Through the Year 2035,” emphasizing the widespread adoption of green production and lifestyles, a steady decline in carbon emissions after peaking, significant improvements in ecological environments, and notable enhancements in ecosystem diversity and stability, ultimately achieving the goal of a “Beautiful China” (Wang et al., 2021). Against this backdrop, analyzing the future changes in ESs is critical for supporting the “dual carbon” goals and advancing ecological civilization. Meanwhile, the ecological environment changes in Shaanxi Province have significant implications for the stability of ecosystems at both the national and global levels (Wang et al., 2020). These ecosystems are crucial in water resource conservation, climate regulation, and biodiversity protection. However, due to complex topography, arid climate, and land degradation, Shaanxi’s ecological environment remains relatively fragile, posing challenges to ecosystem health and human society. Since the beginning of the 21st century, Shaanxi has implemented various environmental policies, including the Grain for Green Program and afforestation initiatives (Cao et al., 2009). Nevertheless, in-depth research on the impact of these environmental policies on ESs remains insufficient, and future trends of ESs under different development policies remain unclear. Therefore, this study selects Shaanxi Province as a representative study area and employs the coupled LightGBM-PLUS model to investigate the dynamic response characteristics of ESs to land-use and LUCC and their potential driving mechanisms. Additionally, by integrating the ESP and Grey Multi-Objective Programming (GMOP), the study further explores optimization patterns for ESs. Specifically, this research aims to predict the impact of LUCC on the WSCH system from 2022 to 2037, revealing the spatiotemporal evolution patterns of ESs and their underlying drivers. The study also examines optimized LUCC schemes suitable for Shaanxi’s future development, providing scientific evidence and guidance for land-use structure optimization and sustainable ESs management.

2 Materials and methods

2.1 Study area

Shaanxi Province, located in the heart of northwestern China (Figure 1), lies in the middle reaches of the Yellow River and covers an area of approximately 205,624 square kilometers (Li and Li, 2022). The region experiences an average annual temperature of 9–16 °C and annual precipitation ranging from 340 to 1,240 mm. Spanning three climatic zones, Shaanxi exhibits diverse natural landscapes, including mountains, hills, basins, and plains, with precipitation decreasing from south to north. The northern mountains and the Qinling Mountains divide Shaanxi into three distinct natural regions: the Loess Plateau (northern Shaanxi), the Guanzhong Plain (central Shaanxi), and the Qinba Mountains (southern Shaanxi). These regions demonstrate significant disparities in economic development and characteristic spatial heterogeneity in land-use patterns (Li et al., 2020). Shaanxi’s ecosystems host diverse flora and fauna, playing an irreplaceable role in HQ maintenance, SC, and WY functions (Song et al., 2017). To mitigate environmental risks associated with land use and LUCC, it is critical to explore optimization strategies for ESs under multiple scenarios. Such efforts not only provide scientific decision-making support for regional sustainable development but also promote a harmonious balance between economic growth and ecological conservation.

Figure 1

2.2 Data source

This study mainly combines natural condition datasets, socioeconomic development datasets, and land use data to achieve multi-scenario simulation of land use and ESs evaluation. The specific data sources are introduced in Table 1.

Land use data (2017 and 2022) are subject to uniform quality control, including geographic correction, visual interpretation and field survey, to ensure that all land use types at all levels meet the accuracy requirements (more than 80%) (Liu et al., 2024). The primary land types are divided into Cropland, Forest, Grassland, Water, Constructed Land, and Bare Land. The National Compilation of Cost and Income of Major Agricultural Products is provided by the National Bureau of Statistics of China¹ to record the production costs and income of major agricultural products. The Shaanxi Statistical Yearbook is published by the Shaanxi Bureau of Statistics² to obtain crop planting area data. To ensure calculation stability and spatial data accuracy consistency, the land cover data are resampled to a resolution of 250 m $\times$ 250 m using the bilinear interpolation method (Shi et al., 2023).

2.3 Research process

Table 2 summarizes the abbreviations used throughout this study. This study follows an integrated technical workflow built upon a four-stage progression: driver identification, spatial constraint construction, scenario-based land-use simulation, and ecosystem service response and mechanism analysis (Figure 2). The methodological framework is structured as follows:

• Driver identification using LightGBM

Figure 2

Fifteen natural and socio-economic variables were evaluated with the LightGBM model to quantify their contributions to land-use transitions. This ensures that the selected drivers are scientifically sound and suitable for subsequent simulations.

• Spatial constraint development via ESP and GMOP

Key ESs (WY, SC, CS, HQ) were assessed with InVEST to derive Ecological Protection Importance (EPI), while Urban Development Suitability (UDS) was constructed to capture development potential. Integrating EPI and UDS yielded the Ecological Security Pattern (ESP). The Grey Multi-Objective Programming (GMOP) model then optimized future land-use demand under joint ecological and economic objectives.

• Scenario-based land-use simulation using PLUS

Incorporating the validated drivers, ESP constraints, and GMOP-optimized demands, the PLUS model simulated four 2037 scenarios: Natural Development (ND), Economic Priority (EP), Ecological Land Protection (ELP), and Coordinated Development (CD). These simulations reveal how alternative policies reshape spatial land-use patterns.

• ES response assessment and mechanism analysis (RDA)

ESs under each scenario were quantified using InVEST. Redundancy Analysis (RDA) was then used to identify dominant natural and socio-economic drivers of ES dynamics, clarifying the mechanisms underlying WSCH changes.

2.4 Research methods

2.4.1 LightGBM

Ensemble learning is an effective machine learning approach that enhances predictive performance by constructing and combining multiple learners (Ganaie et al., 2022). To verify whether the selected driving factors can explain the variations in six types of land use, this study employs the Light Gradient Boosting Machine (LightGBM) model to build a classification framework. We employed the Light Gradient Boosting Machine (LightGBM), an efficient gradient-boosting framework, to evaluate the relative importance of 15 candidate drivers influencing land-use transitions. Compared with other GBDT implementations, such as XGBoost, LightGBM offers higher computational efficiency and lower memory usage when handling large-scale datasets (Hajihosseinlou et al., 2023). For data processing, input samples were randomly partitioned into training (80%) and validation (20%) subsets to evaluate model generalization performance. The constructed LightGBM classification model was applied to both training and testing datasets, yielding classification evaluation results for model performance.

To verify the influence of various driving factors on LUCC, this study, drawing on relevant literature (Liang et al., 2021; Xu et al., 2022; Shi et al., 2023), collected 15 potential driving factors related to the natural environment and socioeconomics. These factors include elevation, slope, average annual precipitation, average annual temperature, NDVI, soil type (content of sand, silt, and clay), soil organic matter content, population density, GDP, nighttime light intensity, distance to water systems, distance to main roads, and distance to railways. The LightGBM model was employed to quantify the influence of each driving factor on different land-use categories, thereby validating the suitability and rationality of factor inputs in the PLUS model.

2.4.2 Construction of ESP

2.4.2.1 Ecological source extraction

The study aims to accurately identify areas critical for ESs, rich in biodiversity, or ecologically fragile, thereby establishing an ESP to emphasize the urgency and importance of ecological protection (Mandle et al., 2021). To this end, four key ESs—WY, SC, CS, and HQ—were selected to construct the WSCH system. These ESs were evaluated using the InVEST model (Shi et al., 2023), and normalization was applied to eliminate dimensional differences. Assuming equal importance for ecological protection, an equal-weight overlay method was employed for comprehensive analysis. Finally, the natural breakpoint method was used to classify the EPI results into five levels. Considering future urban development needs, the study incorporated factors such as topography, climate, living environment, and human activities (Feng et al., 2024; Qi et al., 2024). Thirteen indicators closely related to urban land development suitability were selected. All selected indicators passed high collinearity and significance tests using Pearson Correlation Coefficient (PCC) (Yang et al., 2021). These indicators formed the UDS system. Using the Analytic Hierarchy Process (AHP) to determine indicator weights (Lin et al., 2023) and range normalization for overlay analysis, the regions were ultimately divided into five suitability levels through the natural breaks method. For a detailed description of the EPI and UDS construction, see Appendix A.

To balance the relationship between ecological suitability and urban development, we integrated the EPI and the UDS as key indicators in the identification of ecological sources. By overlaying these two indices, the spatial trade-off between ecological conservation and urban expansion can be effectively characterized. Specifically, areas where the difference between EPI and UDS is greater than or equal to 4 were defined as ecological sources. Such areas generally exhibit high ecological conservation value and limited urban development potential, thus requiring priority protection (Qi et al., 2023).

Nature reserves play a pivotal role in ecological sources, particularly in contributing to ecosystem functions such as WY and SC (Hohenlohe et al., 2021). Therefore, all nature reserves should be incorporated into ecological sources to ensure the long-term effectiveness of their ecological functions. Additionally, as a key protected area for China’s basic farmland, stable cropland areas in Shaanxi since 2010 were excluded during the extraction of ecological sources to avoid conflicts with agricultural land use and ensure the sustained stability of grain production (Ling et al., 2024). To further optimize the spatial layout of ecological sources within the region, GIS technology was employed for spatial analysis. Patches within 500 meters were aggregated, ensuring that any hollow areas had a minimum size of 1 square kilometer. Isolated patches smaller than 1 square kilometer were removed to enhance the continuity of core ecological patches. This approach resulted in a complete and efficient ecological source network (Huang et al., 2021).

2.4.2.2 Resistance surface construction and corridor extraction

The ecological resistance surface was developed by synthesizing both biophysical and human-induced variables that collectively constrain potential species movement pathways (Li et al., 2021). In this study, we selected altitude, slope, land use type and distance from roads and railways, constructed the minimum cumulative resistance model (MCR), and combined it with principal component analysis (PCA) to quantify the ecological resistance surface (Wang et al., 2019). This method uses Equation 1.

Among them, R_MC is the minimum cumulative resistance value, that is, the minimum cumulative resistance from the ecological source to a certain point in the region; f_min is the positive correlation function between the minimum cumulative resistance and the ecological process; D_ij is the spatial distance from the ecological source j to a certain landscape unit i; R_i is the resistance coefficient of a certain landscape unit i in the region to the movement process, which represents the resistance coefficient of the ecological security evaluation index to source diffusion in this study; m is the total number of grid units; n is the total number of sources.

Ecological corridors serve as narrow, linear geographic pathways connecting different ecosystems or habitats (Gregory et al., 2021). Based on circuit theory, this study utilized nodes to represent habitat regions and edges to denote migration routes, with resistance quantifying the connectivity of these paths. To assess corridor importance and network robustness, current flow centrality analysis was conducted using the Circuitscape platform (Nie et al., 2023). This method uses Equation 2.

where 𝐼 represents the current flow through the corridor, 𝑉 denotes the voltage difference between nodes (representing potential habitat connections), and stands for the resistance of the path, which is influenced by factors such as land cover, slope, and anthropogenic disturbance.

2.4.3 Land use demand optimization

GMOP integrates gray system theory with multi-objective optimization, offering a robust framework for decision-making under conditions of multiple objectives and uncertainty (Darvishi et al., 2021). Land use demand optimization often encompasses diverse goals, such as maximizing land resource utilization, ensuring environmental protection, boosting economic benefits, and promoting social equity. The GMOP model provides an effective approach to resolving conflicts between land demand and supply (Fu et al., 2024). Among its key components, the formulation of constraint conditions plays a critical role in defining a feasible solution space that not only meets practical requirements but also adheres strictly to specific rules and limitations. Detailed constraint settings are provided in Appendix A. In this study, the GMOP model is employed to reconcile regional ecological values with economic benefits. This method is based on Equations 3, 4.

Where and the economic benefits and ecological value of Shaanxi, respectively; represents the area of the i-th land use type (km2); and represent the economic benefits and ecological value coefficient per unit area of the i-th land use type (10⁴CNY·km²).

The land use structure needs to be adjusted accordingly to adapt to these two goals so that reaches the optimal ratio. The objective function of GMOP is given by Equation 5.

Where is the development goal of maximizing economic and ecological values, and represent the economic benefits and ecological values of Shaanxi under this goal, respectively.

The ecological value in this study was calculated based on the “ESs Value Coefficient Table per Unit Area of China’s Terrestrial Ecosystem” developed by Xie et al. (2017) and analyzed using relevant statistical yearbook data. The economic benefit coefficients were derived from the GDP generated per unit area of land. Using data from the “Shaanxi Statistical Yearbook,” the total output values of agriculture, forestry, animal husbandry, and fishery were used to represent the economic benefits of cropland, forest, grassland, and water bodies, respectively. For constructed land, the economic benefits were based on the GDP of secondary and tertiary industries, while bare land was assigned an economic benefit of 0.01 million CNY·km² (Ma and Wen, 2021). In order to eliminate the impact of economic activities such as inflation on the research base period and the end period, this study uniformly uses the yearbook data of 2022 to obtain the economic benefit and ecological value coefficient results. Table 3 shows the unit area and corresponding ecological value and economic benefit coefficients of different land use types in Shaanxi in 2022.

2.4.4 Plus

2.4.4.1 Field weight

The Patch-generating Land Use Simulation (PLUS) model combines a Land Expansion Analysis Strategy (LEAS) with a patch-generation algorithm to simulate spatially explicit land-use dynamics under varying development constraints (Gao et al., 2022). Within the PLUS model, the evolution of land use is simulated by deriving the development probabilities of various land use types using the Monte Carlo method. The corresponding Equation 6 is as follows:

Where represents the growth probability of land use type k for grid i; represents the impact of future land use type k demand on grid i, which is an adaptive driving coefficient depending on the difference between the current land quantity at iteration t and the target demand for land use k; represents the neighborhood effect of grid i, indicating the coverage ratio of land use component k in its subsequent neighborhood; h is a random value between 0 and 1; is the threshold for generating new land use patches for land use type k, determined by the model user.

To enhance the effectiveness and reliability of the PLUS model, this study employs a historical scenario-based approach to determine the domain weights required by the model. This method effectively mitigates biases arising from researchers’ subjective judgments, thereby improving the model’s objectivity and scientific rigor (Li Z. et al., 2024). Assuming that the expansion capacity of various land use types remains relatively stable over the same temporal scale, the study quantifies the expansion intensity by calculating the proportion of each land use type’s patch expansion area to the total expansion area during 2017–2022. The TA results are further normalized to establish domain weights for six land use types: Cropland (0.80), Forest (1.00), Grassland (0.00), Water (0.63), Constructed Land (0.71), and Bare Land (0.63).

2.4.4.2 Future scenario settings

Future development objectives will influence the land transition rules and land use simulation outcomes within the model. To comprehensively explore the potential trajectories of future land use, this study establishes four development scenarios for the year 2037 based on the PLUS model (Figure 2): Natural Development (ND), Economic Priority (EP), Ecological Land Protection (ELP), and Coordinated Development (CD).

ND Scenario: In the ND scenario, future land demand is predicted using a Markov chain approach. Specifically, the land use demand for 2037 is derived from the Markov transition matrix probabilities based on land use data from 2017 and 2022. During this period, transitions among the six land use types are allowed.

EP Scenario: The “14th Five-Year Plan for National Economic and Social Development and the Long-Range Objectives Through the Year 2035 of Shaanxi” emphasizes promoting stable and high-quality economic growth. In the EP scenario, economic benefits are maximized by prioritizing urban expansion. Land transitions follow an economic benefit hierarchy, ranked from highest to lowest as: Constructed Land, Cropland, Water, Grassland, Forest Land, and Bare Land. Lower-ranked land types are prohibited from transitioning to higher-ranked ones. The expansion coefficients for primary economic land types (Cropland and Constructed Land) are increased by 20%. Additionally, strict adherence to the Cropland protection policy prohibits Cropland from being converted to other land types (Hao et al., 2024).

ELP Scenario: The “14th Five-Year Plan for Ecological Environmental Protection of Shaanxi” highlights prioritizing ecosystem quality and environmental safety. In the ELP scenario, policies such as forest restoration and natural forest conservation are emphasized (Li H. et al., 2022). Land transitions follow an ecological value hierarchy, ranked from highest to lowest as: Water, Forest, Grassland, Cropland, Bare Land, and Constructed Land. Lower-ranked land types cannot transition to higher-ranked ecological land types. Coupled with the ESP, the expansion coefficients for ecological land types (Forest, Grassland, and Water) are increased by 20% (Wei et al., 2021).

CD Scenario: Balancing high-quality economic development with advanced ecological protection is a cornerstone of China’s ecological civilization strategy (Peng et al., 2020). In the CD scenario, efforts are made to reconcile the conflict between urbanization and ecological conservation. This scenario integrates the ESP and employs the GMOP model to coordinate regional ecological value with economic benefits.

2.4.5 RDA

Previous studies have not clearly elucidated the causes behind the spatiotemporal variation characteristics of ESs (Fang et al., 2021; Shi et al., 2023). RDA, a widely used multivariate statistical method in ecology, integrates the principles of multiple regression analysis and principal component analysis. It is commonly applied to explore the relationships between environmental factors and species composition (Capblancq and Forester, 2021). The primary advantage of RDA lies in its ability to simplify high-dimensional data through dimensionality reduction, thereby extracting key variation patterns and enhancing data interpretability. This makes RDA an essential tool for uncovering the complex relationships between environmental factors and ecosystems (Chen et al., 2019). In this study, 15 environmental variables, including 9 natural factors and 6 social factors, were analyzed to quantify their potential impacts on four types of ESs—WY, SC, CS, and HQ—from 2022 to 2037. Additionally, the study identifies the key driving factors influencing ES changes, providing a comprehensive perspective for understanding the driving mechanisms of ESs.

3 Results

3.1 Model checking

In this study, the LightGBM model was employed to predict multiple land-use categories, and the Receiver Operating Characteristic (ROC) curves were generated using observed land-use data (Figure 3). Model performance was systematically evaluated through the Area Under the Curve (AUC) and the Root Mean Square Error (RMSE). The results indicate that all land-use classes achieved AUC values above 0.85, and the RMSE values remained generally low, demonstrating the model’s strong discriminatory power and robust stability (Guo et al., 2021). Notably, Water and Bare land exhibited exceptionally low RMSE values (0.047 and 0.030, respectively), suggesting minimal prediction error. Although the RMSE for Cropland and Grassland was relatively higher, their AUC values (0.89 and 0.96, respectively) still reflect reliable classification performance overall (Guo et al., 2021). Feature importance analysis further revealed significant differences in driving factors across various land use types. The distribution of Cropland and Forest is primarily driven by natural environmental factors, with key explanatory variables being mean annual precipitation, vegetation cover, and elevation. Grassland distribution is closely associated with precipitation and vegetation cover, while the relatively high contribution of GDP suggests a potential link between Grassland distribution and economic activities, such as livestock farming or tourism. Water distribution is influenced by the combined effects of slope, elevation, and population density. Constructed Land is highly correlated with human activities, with nighttime light, population density, and economic development level (GDP) serving as major driving factors. Bare land distribution is mainly affected by topography (slope and elevation) and spatial distance to water sources, reflecting the combined influence of natural factors and human activities. Overall, natural factors predominantly govern the spatial distribution of land use types, while social factors significantly impact only the distribution of Constructed Land. These findings provide scientific evidence for optimizing regional land resource allocation and formulating sustainable development plans.

Figure 3

To validate the reliability of the model, this study selected nine natural factors and six social factors, and combined them with 2017 land use data to simulate the land use patterns of 2022 using the coupled LightGBM-PLUS model. The simulation results were then compared with the actual 2022 land use data for accuracy validation, employing the Kappa coefficient and Overall Accuracy (OA) for evaluation (Nie et al., 2023). The validation results show that the Overall Accuracy (OA) achieved 0.93, indicating a classification accuracy of 93% across the overall sample, with strong classification performance. The Kappa coefficient reached 0.90, further demonstrating the model’s reliability and high precision. Diagnostic results of the model indicate that the coupled LightGBM-PLUS model exhibits excellent simulation accuracy and classification performance, making it a robust tool for accurately predicting LUCC.

3.2 ESP

Figure 4 presents the spatial distribution of UDS and EPI. High UDS values are primarily located in the Guanzhong Plain, including Baoji, Xi’an, Xianyang, Weinan, and northern Yulin, indicating significant development potential and adaptability in these areas. Conversely, low UDS values are found in southern Shaanxi and parts of Yan’an, predominantly covered by Grassland and Forest. High EPI values are concentrated in the Qinling-Daba Mountains, characterized by their unique ecological environment and biodiversity (Wang et al., 2024), thus warranting priority protection. In contrast, low EPI values are mainly distributed in the Guanzhong Plain and northern Shaanxi, where ecological functions are relatively weak due to the impacts of agriculture and urbanization (Zhu et al., 2022). Ecological source areas, derived based on UDS and EPI, cover an area of 13424.81 km², primarily located in the Qinling-Daba Mountains in southern Shaanxi. This region serves as a core area for ecological protection due to its unique ecological environment and critical ecological functions. A 600-meter buffer zone was subsequently established around these areas to maintain landscape diversity. Using the MCR model and circuit theory, 45 ecological corridors with a total length of 537.62 km were identified. Considering the role of ecological corridors in enhancing ecological flows, a 200-meter buffer zone was established on both sides of the corridors, based on existing studies. Finally, the buffered ecological source areas and ecological corridors were overlaid to construct the ESP. As shown in Figure 4c, the constructed ESP covers an area of 21,784.88 km², accounting for 10.61% of the total study area. The ESP developed in this study effectively preserves the core areas of ESs while considering urban development potential.

Figure 4

3.3 Land use transition matrix under different scenarios

Figure 5 shows the spatial distribution of land use and transition patterns under four scenarios in Shaanxi Province. The overall spatial structure remains consistent, with Forest concentrated in the Qinling–Daba Mountains, Grassland in northern Shaanxi, and Cropland in the Guanzhong Plain. In the baseline year (2022), Forest, Grassland, and Cropland accounted for 46.25, 25.24, and 25.42% of the total area, respectively.

Figure 5

The ND and EP scenarios reveal contrasting development trajectories. Under ND, LUCC is minimal: Cropland remains stable, Forest shows strong persistence, and Grassland transitions mainly follow natural succession processes. In contrast, EP accelerates land development, with Constructed land expanding most rapidly (6777.94 km²), largely at the cost of Forest and Grassland. Although Cropland continues to increase under strengthened protection policies, ecological pressure intensifies significantly due to large-scale conversion of ecological land to built-up areas.

In the ELP and CD scenarios, ecological protection emerges as the dominant driver. ELP promotes substantial ecological restoration, with extensive Cropland converted to Forest and Grassland, and strict limits placed on urban expansion. CD represents a balanced pathway: Cropland remains stable to ensure food security, Forest increases moderately, Grassland decline is alleviated, and Constructed land expands in a controlled manner (5,588.94 km²). Overall, EP imposes the greatest ecological pressure, ELP maximizes ecological gains, ND maintains historical trends, and CD achieves coordinated development between economic and ecological goals.

3.4 Spatial pattern of ESs

From 2022 to 2037, ESs in Shaanxi exhibit pronounced spatial differentiation, consistently showing higher values in the south and mountainous regions than in northern arid and plain areas (Figure 6). WY displays a southwest-to-northeast gradient driven by climatic and hydrological conditions. Although WY remains relatively stable across scenarios, ND and EP show slight declines, with EP reaching the lowest value due to intensified land development. In contrast, the CD scenario achieves the highest WY (1983.27 × 10⁶ mm), indicating that balancing development with ecological constraints effectively safeguards key hydrological functions.

Figure 6

SC is consistently highest in the Qinling Mountains, where terrain, vegetation, and humid climate jointly reduce erosion. Among the scenarios, ELP achieves the greatest SC improvement, reflecting the strong effectiveness of ecological protection in restoring soil quality. EP also shows localized SC enhancement linked to Grassland expansion, while CD achieves moderate gains beyond ND, demonstrating that coordinated land use remains beneficial for erosion control even without strict ecological prioritization.

CS and HQ show strong responses to land development intensity. High-value CS and HQ areas are concentrated in forest- and grassland-dominated regions, particularly the Qinling Mountains and the southern Loess Plateau. EP leads to the sharpest declines in both CS and HQ, underscoring the ecological costs of rapid development. Conversely, ELP delivers the greatest improvements through extensive ecological land restoration, while CD performs nearly as well, achieving substantial gains in CS (1932.31 Tg) and noticeable enhancements in HQ. Overall, the comparative scenario analysis reveals that EP imposes the greatest ecological pressure, ELP maximizes ecological benefits, and CD offers an optimal balance, demonstrating that integrated land-use policies aligned with ESP constraints can effectively enhance ecosystem multifunctionality.

3.5 Ecological and economic trade-offs

Figure 7 illustrates the trends in the total ecological value and total economic benefits from 2022 to 2037 across different scenarios, revealing a significant trade-off relationship between ESs and economic benefits. In the ND scenario, both economic benefits and ecological value show an increase; however, the WY decreases, and the improvement of other ESs is limited, unable to cope with the escalating ecological pressure in the region. This indicates that the traditional land-use development model needs optimization to meet the new ecological and economic demands. In the EP scenario, economic benefits reach their highest value (41,917.51 × 10⁸ CNY), but ecological value drops to its lowest level. While this scenario maximizes economic benefits, it has a significant negative impact on ESs, such as a decrease in WY, CS, and HQ. This suggests that in the EP scenario, economic growth comes at the cost of partial loss in ecosystem functions, highlighting the risks of intensified land development and resource utilization leading to ecological degradation.

Figure 7

The ELP scenario demonstrates a significant increase in ecological value (4708.54 × 10⁸ CNY), making it the scenario with the highest ecological value among all, but its economic benefits are relatively low, amounting to only 34167.93 × 10⁸ CNY. It is the only scenario where total economic value experiences a decline. This outcome results from stricter ecological protection measures that effectively enhance the functions of ESs, but also significantly inhibit economic growth. This illustrates the deep conflict between ecological protection and economic development objectives in policymaking. In contrast, the CD scenario strikes a more balanced relationship between ecological value and economic benefits, with ecological value and economic benefits reaching 4668.02 × 10⁸ CNY and 35158.72 × 10⁸ CNY, respectively. By optimizing land use structure and rationally planning resource allocation, this scenario achieves steady improvements in ESs while maintaining a high level of economic benefits (35158.72 × 10⁸ CNY). The CD scenario embodies a sustainable development pathway, preserving critical ecological function zones while meeting economic growth targets, offering valuable insights for formulating future development strategies.

4 Discussion

4.1 Land use development direction under different scenarios

This study explores the response of ESs to LUCC in Shaanxi from multiple perspectives. Through literature review, machine learning validation, and accuracy analysis, 15 selected factors were identified as effective in explaining the driving mechanisms of LUCC. Among these, temperature, precipitation, NDVI, and GDP exert a significant influence on each land type. The final Kappa coefficient and OA accuracy of the model both exceed 90%, indicating a high level of reliability in the simulation results.

Under the ND scenario, land use pattern changes are minimal, with Cropland and Forest remaining stable. However, Grassland exhibits a significant transition to Cropland and Forest, reflecting the influence of natural driving factors under historical evolution trends. In the EP scenario, economic development demands drive the rapid expansion of Constructed land, leading to a significant reduction in Grassland and Forest areas, thereby exerting greater pressure on the ecological environment. Under the ELP scenario, the ecological benefits of Forests are well preserved, while urban expansion is restricted. Due to the implementation of the Grain for Green policy, the Cropland area has decreased. In Shaanxi, regions with high vegetation coverage are primarily concentrated in the Qinba Mountains, particularly in the Qinling region, which boasts superior ecological conditions. Under this scenario, forest vegetation in the Qinling region of southern Shaanxi is effectively protected and restored.

The spatial distributions of UDS and EPI reveal distinct regional disparities in urbanization potential and ecological conservation priorities within Shaanxi Province. The Guanzhong Plain, characterized by well-developed infrastructure and robust economic growth, exhibits high development potential. Conversely, areas in southern Shaanxi and parts of Yan’an are constrained by complex topography and limited transportation access, resulting in lower UDS values. These contrasts necessitate the formulation of differentiated development strategies. The Qinba Mountain region, as a national key ecological function area (Zhang and Liang, 2020), possesses significant ecological value but is also a contiguous poverty-stricken area, where balancing ecological protection and economic development becomes a core challenge (Li R. et al., 2024). By integrating UDS and EPI to construct the ESP, reasonable constraints can be established in ecologically suitable areas, avoiding unnecessary restrictions on urban construction, while formulating differentiated protection strategies based on the ecological characteristics of different regions, thereby achieving coordinated development of urbanization and ecological protection. The CD scenario using ESP aims to balance economic development with ecological protection by stabilizing Cropland, moderately expanding Constructed land, and rationally protecting ecological land to achieve coordinated development. The implementation of ESP strengthens ecological protection in key areas while allowing for modest growth in Constructed land to meet urbanization demands within the context of economic growth. This scenario not only optimizes the ecological protection pattern but also provides a pathway for regional sustainable development, ensuring that urbanization and ecological security progress in parallel, promoting coordinated development and the construction of ecological civilization.

The LUCC of each scenario reflects the impact of different goal-oriented approaches. The ND scenario emphasizes the continuation of historical trends, while the EP scenario focuses on economic development, leading to greater ecological pressure. The ELP scenario prioritizes ecological protection, significantly expanding ecological land. In the CD scenario, land development policies demonstrate strong adaptability and comprehensiveness, supporting economic growth while effectively maintaining the functions of ESs. This scenario provides an important reference for future land use planning in Shaanxi, particularly in terms of reinforcing ecological protection policies for key areas such as the Qinba Mountains, to achieve a win-win situation for economic, ecological, and social benefits.

4.2 Relationships and potential drivers of WSCH

The PCC analysis of WSCH shows significant synergies between WY, SC, CS, and HQ (Figure 8a). A healthy soil structure and vegetation cover help to enhance water source conservation capacity, reduce soil erosion, and simultaneously improve CS (Abdallah et al., 2021). The stable supply of water sources promotes plant growth, which in turn enhances carbon storage capacity. Soil conservation not only protects soil organic matter but also improves the long-term carbon storage potential, while increased vegetation cover helps to improve soil structure and enhance SC (Francaviglia et al., 2023). As an indicator of biodiversity, HQ has the strongest correlation with CS. Water, soil, carbon, and habitat form an interconnected ecological network, collectively influencing the overall function and health of the ecosystem.

Figure 8

The study of the spatiotemporal dynamics of ESs is a scientific basis for formulating ecological protection policies. However, previous studies have often been limited to the analysis of single factors and have not systematically revealed the changes under the combined effect of multiple factors (Liu et al., 2019). RDA as a multivariate statistical method, can effectively explore the relationships between multiple explanatory variables and response variables. This study explores the potential driving factors of ES changes in Shaanxi from 2022 to 2037 based on 15 selected variables, including 9 natural factors and 6 socio-economic factors. As shown in Figure 8b, the redundancy analysis (RDA) explains over 70% of the variance across the entire study area, with the majority of the driving factors exhibiting statistically significant effects (p < 0.001), indicating that these factors have a pronounced influence on changes in ESs (Shi et al., 2023). Among them, slope (r = 0.23 ~ 0.22, p < 0.01) and precipitation (r = 0.22 ~ 0.21, p < 0.01) were identified as the two factors that contributed the most to the overall changes in the four ESs from 2022 to 2037. The study found that in both the 2022 and 2037 CD scenario, slope is a key factor influencing SC, while precipitation has the most significant effect on WY. Figure 8b further reveals the negative impacts of nighttime lights, GDP, and population density on HQ and CS, with HQ showing a highly significant negative correlation with nighttime lights. In the 2037 CD scenario, the impact of NDVI and altitude on ESs increased compared to 2022. The direction of the arrows in the figure reflects the positive or negative effects of the driving factors on ESs, while the arrow length indicates the intensity of the effect, i.e., the contribution rate of the variable’s explanation.

The factor contribution results reveal the key roles played by topographical conditions and climate in regulating ESs (Figure 8c). Slope determines the spatial distribution of SC and WY. Steep slope areas are more prone to soil erosion due to gravity, while gentle slope areas are more conducive to the stable retention of soil and water (Han et al., 2019). Changes in precipitation not only directly affect the water yield capacity but also indirectly influence CS and HQ by regulating vegetation growth and surface runoff (Jia et al., 2024). Although the changes in Shaanxi’s ESs are mainly driven by natural factors, the negative impacts of socio-economic factors should not be overlooked. Future ecological protection must comprehensively consider both natural and human activity influences.

4.3 Spatiotemporal sequence analysis of ESs

In future development, the spatiotemporal sequence analysis of ESs reveals the dynamic evolution characteristics and spatial differentiation patterns of four ES functions under different scenarios. The study indicates that between 2022 and 2037, WY, SC, CS, and HQ are driven by climate, topography, and LUCC, showing significant regional differences with the south performing better than the north, and mountainous areas outperforming plains. In the various scenarios, the ND scenario shows some improvement in both economic benefits and ecological value, but the enhancement of ESs is very limited. The limitations of the traditional land use development model make it difficult to address the increasing ecological pressures in the future (Long et al., 2021). In contrast, the EP scenario seeks to maximize economic benefits (41917.51 × 10⁸ CNY), but ecological value declines to its lowest point, with key ecological functions such as WY and CS significantly degraded, reflecting the ecological costs brought by rapid economic growth.

In the ELP scenario, ESs’ overall level is significantly improved, especially in SC and HQ. Through strict protection measures, this scenario achieves the highest ecological value (4708.54 × 10⁸ CNY), but economic benefits fall to 34167.93 × 10⁸ CNY, highlighting the suppressive effect of the ecological priority policy on economic growth. The CD scenario performs well across multiple ESs. By optimizing land use structure and reasonably allocating resources, it effectively balances ecological value and economic benefit, demonstrating a sustainable development path.

Recent studies on watershed dynamics, soil conditions and pollution patterns underscore that balancing social development with ecological conservation requires integrated, evidence-based land management. Morphometric analyses indicate that watershed fragility and erosion risks must be incorporated into regional planning (Shoumik et al., 2025), while advances in plant growth-promoting microbial technologies offer viable pathways to sustain agricultural productivity with reduced chemical inputs (Shoumik et al., 2025). In parallel, research on antibiotic removal, heavy-metal pollution control and saline-alkali soil remediation highlights the critical role of low-cost treatment technologies and soil-quality restoration in maintaining ecosystem functioning (Asghar et al., 2023; Ilić et al., 2024). Moving forward, a deeper understanding of the spatiotemporal evolution of ESs, combined with systematic monitoring, pollution mitigation and adaptive management, will be essential for aligning ecological enhancement with socioeconomic needs and for providing a scientific basis for differentiated ecological-protection policies and optimized land-use strategies.

4.4 Limitation

The 15 driving factors selected in this study cover highly correlated natural factors and socio-economic development factors. The diagnostic results of these driving factors indicate that the selection is reasonable. However, the interactions between these factors were not fully considered, which may introduce some uncertainty in the simulation results. Furthermore, although the four development scenarios explored in this study provide a reference for future predictions, they do not cover all possible outcomes.

Future research should enhance ES assessments by integrating additional models and algorithms, such as the SWAT model (Akoko et al., 2021), while explicitly accounting for climate change impacts on LUCC to capture more comprehensive ES responses. Strengthening collaboration with regional land-planning authorities is crucial to incorporate local policy constraints and develop LUCC strategies that reflect practical development needs, thereby providing a scientific basis for CD scenario design and informing regional land-use and ecological protection policies. Moreover, uncertainties arising from inconsistent spatial resolution among datasets and the omission of future climate variability limit the robustness of current ES estimates (Zamora-Maldonado et al., 2025); integrating SSP-RCP climate scenarios into PLUS and InVEST simulations would improve temporal reliability and strengthen scenario-based projections.

5 Conclusion

In recent years, the rapid industrialization and urbanization in Shaanxi have placed significant pressure on the ecological environment. In this context, this study utilizes the coupled LightGBM-PLUS model to simulate future LUCC and assesses the spatiotemporal differentiation of four ESs—WY, SC, CS, and HQ—under different scenarios for 2022 to 2037. Furthermore, the study evaluates the effectiveness of ESP-GMOP optimization in enhancing ESs. The results show that the LightGBM-PLUS model demonstrates excellent performance in simulations. Under future scenarios, all four ESs follow a spatial pattern of “lower in the north, higher in the south, and with mountainous regions performing better than plains.” Scenario comparisons reveal that the CD scenario, through GMOP optimization of land use structure and ESP protection in core areas, achieves a sustainable advantage by balancing the enhancement of ESs with economic development. This scenario avoids the negative aspects of the ELP scenario, which imposes overly restrictive measures on economic development, and mitigates the risks associated with the EP scenario, which prioritizes economic benefits at the cost of ecological degradation. Under the CD scenario, controlled urban expansion and optimized land use significantly enhance WY, SC, CS, and HQ while ensuring food security. Land-use optimization under this scenario maintains stable Cropland and prevents excessive conversion to Constructed land, which is critical for regional food security. By strengthening soil conservation and improving water-use efficiency, the CD scenario further supports sustainable agricultural production, linking land-use planning with the long-term resilience of the food system. The RDA analysis further indicates that natural factors are the primary drivers of ESs changes, whereas socio-economic factors primarily exert negative effects. The ESs optimization strategy proposed in this study—by optimizing land use structure and rational resource allocation—achieves a win-win situation for both ecology and economy, providing a scientific basis for the sustainable development of regional ecological resources.

References

• 1

  AbdallahA. M.JatH. S.ChoudharyM.AbdelatyE. F.SharmaP. C.JatM. L. (2021). Conservation agriculture effects on soil water holding capacity and water-saving varied with management practices and agroecological conditions: a review. Agronomy11:1681. doi: 10.3390/agronomy11091681

  • CrossRef
  • Google Scholar

• 2

  AkokoG.LeT. H.GomiT.KatoT. (2021). A review of SWAT model application in Africa. Water13:1313. doi: 10.3390/w13091313

  • CrossRef
  • Google Scholar

• 3

  AniahP.BawakyillenuoS.CodjoeS. N. A.DzankuF. M. (2023). Land use and land cover change detection and prediction based on CA-Markov chain in the savannah ecological zone of Ghana. Environ. Chall.10:100664. doi: 10.1016/j.envc.2022.100664

  • CrossRef
  • Google Scholar

• 4

  AsgharI.AhmedM.FarooqM. A.IshtiaqM.ArshadM.AkramM.et al. (2023). Characterizing indigenous plant growth promoting bacteria and their synergistic effects with organic and chemical fertilizers on wheat (Triticum aestivum). Front. Plant Sci.14:1232271. doi: 10.3389/fpls.2023.1232271,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 5

  CabernardL.PfisterS.HellwegS. (2024). Biodiversity impacts of recent land-use change driven by increases in Agri-food imports. Nat. Sustain.7, 1512–1524. doi: 10.1038/s41893-024-01433-4

  • CrossRef
  • Google Scholar

• 6

  CaoS.XuC.ChenL.WangX. (2009). Attitudes of farmers in China’s northern Shaanxi Province towards the land-use changes required under the grain for green project, and implications for the project’s success. Land Use Policy26, 1182–1194. doi: 10.1016/j.landusepol.2009.02.006

  • CrossRef
  • Google Scholar

• 7

  CapblancqT.ForesterB. R. (2021). Redundancy analysis: a Swiss Army knife for landscape genomics. Methods Ecol. Evol.12, 2298–2309. doi: 10.1111/2041-210X.13722

  • CrossRef
  • Google Scholar

• 8

  CastillónF.RauP.BourrelL.FrappartF. (2025). Dynamics and patterns of land cover change in the Piura River basin (Peruvian Pacific slope and coast) in the last two decades. Front. Remote Sens.6:44. doi: 10.3389/frsen.2025.1529044

  • CrossRef
  • Google Scholar

• 9

  ChenH. W.LinH. C.ChuangY. H.SunC. T.ChenW. Y.KaoC. Y. (2019). Effects of environmental factors on benthic species in a coastal wetland by redundancy analysis. Ocean Coast. Manag.169, 37–49. doi: 10.1016/j.ocecoaman.2018.12.003

  • CrossRef
  • Google Scholar

• 10

  DarvishiD.LiuS.Yi-Lin ForrestJ. (2021). Grey linear programming: a survey on solving approaches and applications. Grey Syst. Theory Appl.11, 110–135. doi: 10.1108/GS-04-2020-0043

  • CrossRef
  • Google Scholar

• 11

  EekhoutJ. P.de VenteJ. (2022). Global impact of climate change on soil erosion and potential for adaptation through soil conservation. Earth-Sci. Rev.226:103921. doi: 10.1016/j.earscirev.2022.103921

  • CrossRef
  • Google Scholar

• 12

  FangL.WangL.ChenW.SunJ.CaoQ.WangS. (2021). Identifying the impacts of natural and human factors on ecosystem service in the Yangtze and Yellow River basins. J. Clean. Prod.314:127995. doi: 10.1016/j.jclepro.2021.127995

  • CrossRef
  • Google Scholar

• 13

  FengY.ZhangW.YuJ.ZhuoR.. (2024). Optimization of land-use pattern based on suitability and trade-offs between land development and protection: A case study of the Hohhot-Baotou-Ordos (HBO) area in Inner Mongolia, China. J. Clean. Prod, 466:142796. doi: 10.1016/j.jclepro.2024.142796

  • CrossRef
  • Google Scholar

• 14

  FrancavigliaR.AlmagroM.Vicente-VicenteJ. L. (2023). Conservation agriculture and soil organic carbon: principles, processes, practices and policy options. Soil Syst.7:17. doi: 10.3390/soilsystems7010017

  • CrossRef
  • Google Scholar

• 15

  FuH.LiangY.ChenJ.ZhuL.FuG. (2024). A new framework of land use simulation for land use benefit optimization based on GMOP-PLUS model—a case study of Haikou. Land13:1257. doi: 10.3390/land13081257

  • CrossRef
  • Google Scholar

• 16

  FuC.XuM. (2023). Achieving carbon neutrality through ecological carbon sinks: a systems perspective. Green Carbon1, 43–46. doi: 10.1016/j.greenca.2023.08.005

  • CrossRef
  • Google Scholar

• 17

  GanaieM. A.HuM.MalikA. K.TanveerM.SuganthanP. N. (2022). Ensemble deep learning: a review. Eng. Appl. Artif. Intell.115:105151. doi: 10.1016/j.engappai.2022.105151

  • CrossRef
  • Google Scholar

• 18

  GaoL.TaoF.LiuR.WangZ.LengH.ZhouT. (2022). Multi-scenario simulation and ecological risk analysis of land use based on the PLUS model: a case study of Nanjing. Sustain. Cities Soc.85:104055. doi: 10.1016/j.scs.2022.104055

  • CrossRef
  • Google Scholar

• 19

  GregoryA.SpenceE.BeierP.GardingE. (2021). Toward best management practices for ecological corridors. Land10:140. doi: 10.3390/land10020140

  • CrossRef
  • Google Scholar

• 20

  GuoZ.ShiY.HuangF.FanX.HuangJ. (2021). Landslide susceptibility zonation method based on C5. 0 decision tree and K-means cluster algorithms to improve the efficiency of risk management. Geosci. Front.12:101249. doi: 10.1016/j.gsf.2021.101249

  • CrossRef
  • Google Scholar

• 21

  HajihosseinlouM.MaghsoudiA.GhezelbashR. (2023). A novel scheme for mapping of MVT-type Pb–Zn prospectivity: LightGBM, a highly efficient gradient boosting decision tree machine learning algorithm. Nat. Resour. Res.32, 2417–2438. doi: 10.1007/s11053-023-10249-6

  • CrossRef
  • Google Scholar

• 22

  HanZ.ZhongS.NiJ.ShiZ.WeiC. (2019). Estimation of soil erosion to define the slope length of newly reconstructed gentle-slope lands in hilly mountainous regions. Sci. Rep.9:4676. doi: 10.1038/s41598-019-41405-9,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 23

  HaoS.WangG.YangY.ZhaoS.HuangS.LiuL.et al. (2024). Promoting grain production through high-standard farmland construction: evidence in China. J. Integr. Agric.23, 324–335. doi: 10.1016/j.jia.2023.11.021

  • CrossRef
  • Google Scholar

• 24

  HasanS. S.ZhenL.MiahM. G.AhamedT.SamieA. (2020). Impact of land use change on ecosystem services: a review. Environ. Dev.34:100527. doi: 10.1016/j.envdev.2020.100527

  • CrossRef
  • Google Scholar

• 25

  HohenloheP. A.FunkW. C.RajoraO. P. (2021). Population genomics for wildlife conservation and management. Mol. Ecol.30, 62–82. doi: 10.1111/mec.15720,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 26

  HuangX.WangH.ShanL.XiaoF. (2021). Constructing and optimizing urban ecological network in the context of rapid urbanization for improving landscape connectivity. Ecol. Indic.132:108319. doi: 10.1016/j.ecolind.2021.108319

  • CrossRef
  • Google Scholar

• 27

  HuangA.XuY.LiuC.LuL.ZhangY.SunP.et al. (2019). Simulated town expansion under ecological constraints: a case study of Zhangbei County, Heibei Province, China. Habitat Int.91:101986. doi: 10.1016/j.habitatint.2019.05.005

  • CrossRef
  • Google Scholar

• 28

  IlićP.IlićS.RashidA.MushtaqZ.Mrazovac KurilićS.Stojanović BjelićL.et al. (2024). Exposure levels, health risks, spatially distribution, multivariate statistics and positive matrix factorization model of heavy metals from wild solid waste dumpsites. Water Air Soil Pollut.235:648. doi: 10.1007/s11270-024-07441-6

  • CrossRef
  • Google Scholar

• 29

  Jat BalochM. Y.BaidyaP.AryalM.Moeen-ud-dinM.YangL.IqbalJ.et al. (2026). Fate and transport of viruses in the subsurface environment: a systematic review of pollution pathways in saturated and unsaturated porous media. Environ. Res.288:123163. doi: 10.1016/j.envres.2025.123163,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 30

  JiaZ.LinT.GuoX.ZhengY.GengH.ZhangJ.et al. (2024). Vegetation greening mitigates the positive impacts of climate change on water availability in Northwest China. J. Hydrol.644:132086. doi: 10.1016/j.jhydrol.2024.132086

  • CrossRef
  • Google Scholar

• 31

  KangJ.ZhangX.ZhuX.ZhangB. (2021). Ecological security pattern: a new idea for balancing regional development and ecological protection. A case study of the Jiaodong peninsula, China. Glob. Ecol. Conserv.26:e01472. doi: 10.1016/j.gecco.2021.e01472

  • CrossRef
  • Google Scholar

• 32

  LiM.CaoX.LiuD.FuQ.LiT.ShangR. (2022). Sustainable management of agricultural water and land resources under changing climate and socio-economic conditions: a multi-dimensional optimization approach. Agric. Water Manag.259:107235. doi: 10.1016/j.agwat.2021.107235

  • CrossRef
  • Google Scholar

• 33

  LiR.ChenJ.YangX.YinS.ShiR.BaiY.et al. (2024). The impact of population change on social-ecological systems’ vulnerability: a case of the Qinling-Daba Mountains of southern Shaanxi in China. J. Clean. Prod.476:143682. doi: 10.1016/j.jclepro.2024.143682

  • CrossRef
  • Google Scholar

• 34

  LiC.FangS.GengX.YuanY.ZhengX.ZhangD.et al. (2023). Coastal ecosystem service in response to past and future land use and land cover change dynamics in the Yangtze river estuary. J. Clean. Prod.385:135601. doi: 10.1016/j.jclepro.2022.135601

  • CrossRef
  • Google Scholar

• 35

  LiZ.JiangW.PengK.WangX.DengY.YinX.et al. (2024). Comparative analysis of land use change prediction models for land and fine wetland types: taking the wetland cities Changshu and Haikou as examples. Landsc. Urban Plan.243:104975. doi: 10.1016/j.landurbplan.2023.104975

  • CrossRef
  • Google Scholar

• 36

  LiF.LiX. (2022). An empirical analysis on regional natural gas market of China from a spatial pattern and social network perspective. Energy244:122598. doi: 10.1016/j.energy.2021.122598

  • CrossRef
  • Google Scholar

• 37

  LiY.LiF.YangF.XieX.YinL. (2020). Spatiotemporal impacts of climate change on food production: case study of Shaanxi Province. China. Environ. Sci. Pollut. Res.27, 19826–19835. doi: 10.1007/s11356-020-08447-3,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 38

  LiF.LiuH.WuS.WangY.XuZ.YuP.et al. (2023). A PES framework coupling socioeconomic and ecosystem dynamics from a sustainable development perspective. J. Environ. Manag.329:117043. doi: 10.1016/j.jenvman.2022.117043,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 39

  LiH.ZhangT.CaoX.-S.ZhangQ.-Q. (2022). Establishing and optimizing the ecological security pattern in Shaanxi Province (China) for ecological restoration of land space. Forests13:766. doi: 10.3390/f13050766

  • CrossRef
  • Google Scholar

• 40

  LiY.-Y.ZhangY.-Z.JiangZ.-Y.GuoC.-X.ZhaoM.-Y.YangZ.-G.et al. (2021). Integrating morphological spatial pattern analysis and the minimal cumulative resistance model to optimize urban ecological networks: a case study in Shenzhen City, China. Ecol. Process.10:63. doi: 10.1186/s13717-021-00332-2

  • CrossRef
  • Google Scholar

• 41

  LiangX.GuanQ.ClarkeK. C.LiuS.WangB.YaoY. (2021). Understanding the drivers of sustainable land expansion using a patch-generating land use simulation (PLUS) model: a case study in Wuhan, China. Comput. Environ. Urban. Syst.85:101569. doi: 10.1016/j.compenvurbsys.2020.101569

  • CrossRef
  • Google Scholar

• 42

  LiaoG.HeP.GaoX.LinZ.HuangC.ZhouW.et al. (2022). Land use optimization of rural production–living–ecological space at different scales based on the BP–ANN and CLUE–S models. Ecol. Indic.137:108710. doi: 10.1016/j.ecolind.2022.108710

  • CrossRef
  • Google Scholar

• 43

  LinL.WeiX.LuoP.WangS.KongD.YangJ. (2023). Ecological security patterns at different spatial scales on the loess plateau. Remote Sens15:1011. doi: 10.3390/rs15041011

  • CrossRef
  • Google Scholar

• 44

  LingL.TangH.ChenX.LiS.HanX. (2024). Spatial zoning and effect evaluation of county high-standard farmland siting delineation for sustainable cultivated land use in China: a case study in Dali, Shaanxi. Ecol. Indic.167:112647. doi: 10.1016/j.ecolind.2024.112647

  • CrossRef
  • Google Scholar

• 45

  LiuY.GaoY.LiuL.SongC.AiD. (2022). Nature-based solutions for urban expansion: integrating ecosystem services into the delineation of growth boundaries. Habitat Int.124:102575. doi: 10.1016/j.habitatint.2022.102575

  • CrossRef
  • Google Scholar

• 46

  LiuY.HouX.LiX.SongB.WangC. (2020). Assessing and predicting changes in ecosystem service values based on land use/cover change in the Bohai Rim coastal zone. Ecol. Indic, 111:106004. doi: 10.1016/j.ecolind.2019.106004

  • CrossRef
  • Google Scholar

• 47

  LiuJ.RenY.ChenX. (2024). Regional accuracy assessment of 30-meter GLC_FCS30, GlobeLand30, and CLCD products: a case study in Xinjiang area. Remote Sens16:82. doi: 10.3390/rs16010082

  • CrossRef
  • Google Scholar

• 48

  LiuC.SunW.LiP. (2022). Characteristics of spatiotemporal variations in coupling coordination between integrated carbon emission and sequestration index: a case study of the Yangtze River Delta, China. Ecol. Indic.135:108520. doi: 10.1016/j.ecolind.2021.108520

  • CrossRef
  • Google Scholar

• 49

  LiuW.ZhanJ.ZhaoF.YanH.ZhangF.WeiX. (2019). Impacts of urbanization-induced land-use changes on ecosystem services: a case study of the Pearl River Delta metropolitan region, China. Ecol. Indic.98, 228–238. doi: 10.1016/j.ecolind.2018.10.054

  • CrossRef
  • Google Scholar

• 50

  LongH.ZhangY.MaL.TuS. (2021). Land use transitions: progress, challenges and prospects. Land10:903. doi: 10.3390/land10090903

  • CrossRef
  • Google Scholar

• 51

  LuoQ.ZhangJ.BaoY.ZhangY.YuJ.LiJ.et al. (2025). Multi-scenario simulation of land use optimization based on ecosystem services and ecological security patterns in the Liaohe River basin. Front. Environ. Sci.13:1647039. doi: 10.3389/fenvs.2025.1647039

  • CrossRef
  • Google Scholar

• 52

  MaS.WenZ. (2021). Optimization of land use structure to balance economic benefits and ecosystem services under uncertainties: a case study in Wuhan, China. J. Clean. Prod.311:127537. doi: 10.1016/j.jclepro.2021.127537

  • CrossRef
  • Google Scholar

• 53

  MandleL.Shields-EstradaA.Chaplin-KramerR.MitchellM. G.BremerL. L.GourevitchJ. D.et al. (2021). Increasing decision relevance of ecosystem service science. Nat. Sustain.4, 161–169. doi: 10.1038/s41893-020-00625-y

  • CrossRef
  • Google Scholar

• 54

  NieW.XuB.YangF.ShiY.LiuB.WuR.et al. (2023). Simulating future land use by coupling ecological security patterns and multiple scenarios. Sci. Total Environ.859:160262. doi: 10.1016/j.scitotenv.2022.160262,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 55

  PengB.ShengX.WeiG. (2020). Does environmental protection promote economic development? From the perspective of coupling coordination between environmental protection and economic development. Environ. Sci. Pollut. Res.27, 39135–39148. doi: 10.1007/s11356-020-09871-1,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 56

  QiW.HuY.LinshengZ.HuiW. (2023). Optimising the relationship between ecological protection and human development through functional zoning. Biol. Conserv.281:110001. doi: 10.1016/j.biocon.2023.110001

  • CrossRef
  • Google Scholar

• 57

  QiT.LiY.HuangM.LuoB.PengZ.WangW.et al. (2024). Land intensification use scenarios based on urban land suitability assessment of the national park. Sustain. Cities Soc.102:105229. doi: 10.1016/j.scs.2024.105229

  • CrossRef
  • Google Scholar

• 58

  QuS.HanL.LiL. (2025). Regional responses of ecosystem service security to land use changes and driving mechanisms: insights from nearly 40 years of observations in Shaanxi, China. J. Environ. Chem. Eng.13:116224. doi: 10.1016/j.jece.2025.116224

  • CrossRef
  • Google Scholar

• 59

  ShengS.HuangJ. (2025). Urban expansion and the loss of potential crop yield in the North China plain: implications for regional food security (1980–2020). Front. Sustain. Food Syst.9:1545907. doi: 10.3389/fsufs.2025.1545907

  • CrossRef
  • Google Scholar

• 60

  ShiM.WuH.JiangP.ZhengK.LiuZ.DongT.et al. (2023). Food-water-land-ecosystem nexus in typical Chinese dryland under different future scenarios. Sci. Total Environ.880:163183. doi: 10.1016/j.scitotenv.2023.163183,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 61

  ShoumikB. A. A.IslamM. S.Jat BalochM. Y. (2025). Morphometric analysis and prioritisation of the Punarbhaba-Atrai-Jamuna River basins in the Northwest Bangladesh for soil conservation. Lakes Reserv.30:e70005. doi: 10.1111/lre.70005

  • CrossRef
  • Google Scholar

• 62

  SongB.RobinsonG. M.ZhouZ. (2017). Agricultural transformation and ecosystem services: a case study from Shaanxi Province, China. Habitat Int.69, 114–125. doi: 10.1016/j.habitatint.2017.09.008

  • CrossRef
  • Google Scholar

• 63

  WangQ.GuanQ.SunY.DuQ.XiaoX.LuoH.et al. (2023). Simulation of future land use/cover change (LUCC) in typical watersheds of arid regions under multiple scenarios. J. Environ. Manag.335:117543. doi: 10.1016/j.jenvman.2023.117543,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 64

  WangY.GuoC.ChenX.JiaL.GuoX.ChenR.et al. (2021). Carbon peak and carbon neutrality in China: goals, implementation path and prospects. China Geol.4, 720–746. doi: 10.31035/cg2021083

  • CrossRef
  • Google Scholar

• 65

  WangH.LiuG.LiZ.ZhangL.WangZ. (2020). Processes and driving forces for changing vegetation ecosystem services: insights from the Shaanxi Province of China. Ecol. Indic.112:106105. doi: 10.1016/j.ecolind.2020.106105

  • CrossRef
  • Google Scholar

• 66

  WangH.PengP.KongX.ZhangT.YiG. (2019). Evaluating the suitability of urban expansion based on the logic minimum cumulative resistance model: a case study from Leshan, China. ISPRS Int. J. Geo Inf.8:291. doi: 10.3390/ijgi8070291

  • CrossRef
  • Google Scholar

• 67

  WangX.WangX.TuY.YaoW.ZhouJ.JiaZ.et al. (2024). Systematic conservation planning considering ecosystem services can optimize the conservation system in the Qinling-Daba Mountains. J. Environ. Manag.368:122096. doi: 10.1016/j.jenvman.2024.122096,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 68

  WeiH.LiL.NianM. (2021). China’s urbanization strategy and policy during the 14th five-year plan period. Chin. J. Urban Environ. Stud.9:2150002. doi: 10.1142/S2345748121500020

  • CrossRef
  • Google Scholar

• 69

  XieG.ZhangC.ZhenL.ZhangL. (2017). Dynamic changes in the value of China’s ecosystem services. Ecosyst. Serv.26, 146–154. doi: 10.1016/j.ecoser.2017.06.010

  • CrossRef
  • Google Scholar

• 70

  XuL.LiuX.TongD.LiuZ.YinL.ZhengW. (2022). Forecasting urban land use change based on cellular automata and the PLUS model. Land11:652. doi: 10.3390/land11050652

  • CrossRef
  • Google Scholar

• 71

  YangY. (2021). Evolution of habitat quality and association with land-use changes in mountainous areas: a case study of the Taihang Mountains in Hebei Province, China. Ecol. Indic.129:107967. doi: 10.1016/j.ecolind.2021.107967

  • CrossRef
  • Google Scholar

• 72

  YangX.MengF.FuP.ZhangY.LiuY. (2021). Spatiotemporal change and driving factors of the eco-environment quality in the Yangtze River basin from 2001 to 2019. Ecol. Indic.131:108214. doi: 10.1016/j.ecolind.2021.108214

  • CrossRef
  • Google Scholar

• 73

  Zamora-MaldonadoH. C.Avila-FoucatV. S.Sánchez-SotomayorV. G. (2025). Modeling climate change impacts on the potential distribution of bighorn sheep in Mexico. Front. Clim.7:1386632. doi: 10.3389/fclim.2025.1386632

  • CrossRef
  • Google Scholar

• 74

  ZhangZ.LiJ. (2022). Spatial suitability and multi-scenarios for land use: simulation and policy insights from the production-living-ecological perspective. Land Use Policy119:106219. doi: 10.1016/j.landusepol.2022.106219

  • CrossRef
  • Google Scholar

• 75

  ZhangY.LiangC. (2020). Analysis of annual and seasonal precipitation variation in the Qinba Mountain area, China. Sci. Rep.10:961. doi: 10.1038/s41598-021-03607-y,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 76

  ZhangY.YuP.TianY.ChenH.ChenY. (2023). Exploring the impact of integrated spatial function zones on land use dynamics and ecosystem services tradeoffs based on a future land use simulation (FLUS) model. Ecol. Indic.150:110246. doi: 10.1016/j.ecolind.2023.110246

  • CrossRef
  • Google Scholar

• 77

  ZhuL. L.LiY. P.LiangL. U.LiS. J.RenH. Y. (2022). Spatial heterogeneity and influencing factors of HFRS epidemics in rural and urban areas: a study in Guanzhong plain of Shaanxi Province, China. Biomed. Environ. Sci.35, 1012–1024. doi: 10.3967/bes2022.130,

  • Pubmed Abstract
  • CrossRef
  • Google Scholar