Correction: Revealing urban-rural sustainability dynamics based on multi-source data and machine learning: spatio-temporal hotspots, driving mechanisms, and non-linear thresholds in Suzhou, China
Year: 2026
Type: erratum
Abstract: Urbanisation is one of the primary drivers of land-use transformation in contemporary society, reshaping both urban and rural landscapes throughout the 20th century (Nuissl and Siedentop, 2021). Although urbanisation drives economic growth and infrastructure advancement, it simultaneously leads to extensive transitions from rural to urban land uses, inevitably posing profound challenges to the sustainable development of land-use systems, particularly in peri-urban areas (Fu et al., 2021). These transitional zones, situated between urban and rural systems, integrate land, ecological resources, and human activities related to production and living. They are critical components of regional development (Zhang et al., 2020) and have significant impacts on human health and well-being (Barton, 2009). In the Chinese context, these processes unfold against a longstanding institutional separation between urban and rural areas, shaped by the household registration (hukou) system, differentiated land-use practices, economic structures and socio-cultural characteristics (Li, 2012).Rapid urbanisation has accelerated land-use transformations in peri-urban areas, shifting landscapes from primarily agricultural functions toward residential, industrial, and commercial uses. Development models focused on economic growth, to some extent, overlook the land-use conflicts resulting from such expansion and exacerbate their negative impacts (He et al., 2020).Existing studies on urban-rural land-use transitions can be broadly categorised into two perspectives. The first perspective examines how land-use change in peri-urban areas reshapes economic, ecological and social outcomes. Empirical work has assessed the efficiency and effectiveness of land-use transformation (Fu et al., 2021), the ecological consequences of land-use changes and land-use intensity (Wu et al., 2024;Xu et al., 2020), and broader sustainability implications, including environmental degradation, habitat fragmentation and the loss of cultural landscape identity (Shao et al., 2020;Xu et al., 2020). International research further highlights that unsustainable land-use transformations in rural areas during urbanisation can lead to displacement (Salem et al., 2020), infrastructure deficits, and widening socioeconomic disparities (Dadashpoor and Ahani, 2019). Taken together, this perspective demonstrates that peri-urban land-use transitions are crucial to the sustainability of urban-rural regions and have a direct impact on human well-being. However, most studies address economic, ecological and social dimensions separately or treat them as loosely connected outcome indicators, paying limited attention to how these dimensions interact and co-evolve over time. As a result, the coupled dynamics of "coordination-conflict" between land-use transitions and multi-dimensional sustainability outcomes remain insufficiently understood, particularly in rapidly urbanising contexts such as China.A second perspective focuses on governance arrangements, planning instruments and assessment frameworks for managing land-use change in urban-rural interfaces. Scholars have highlighted that current landuse transformation processes are often governed by fragmented and overlapping institutional regimes, leading to overlapping jurisdictions, inefficient decision-making and weak coordination across administrative boundaries (Perrin et al., 2018). Additionally, Follmann et al. (2021) and Ahani and Dadashpoor (2021) note that existing peri-urban land-use assessment and management frameworks fail to address the dynamic realities of urbanisation, creating loopholes for informal land speculation, unauthorised urban expansion, and environmental degradation. Although this line of research has significantly advanced the understanding of governance deficits and institutional complexity, it tends to emphasise qualitative institutional analysis or singledimensional indicators. However, the foundation of sustainable development lies in the coordination between economic, social, and environmental factors, with the core being the balance between ecological considerations and other dimensions (Gan et al., 2020;Li et al., 2022). There is a lack of attention to operational, quantitative frameworks that can systematically link land-use structures to economic vitality, ecological quality, and social well-being, and that can identify when and how urban-rural systems shift from coordinated development to conflictual outcomes (Buzási and Csete, 2017;Keith et al., 2023). Consequently, despite a substantial body of work on land-use transformation, ecological impacts, planning and control mechanisms, a comprehensive evaluation framework that integrates these dimensions to support sustainable development remains lacking (Salem et al., 2025).In addition to these theoretical gaps, there are notable limitations in the methodological approaches employed in the existing research. Currently, three categories of quantitative approaches are commonly used to evaluate urban-rural sustainability and land-use dynamics. The first category comprises statistical and spatial econometric models, including fixed-effects and random-effects models, as well as spatial panel specifications.The Spatial Durbin Model (SDM) has been widely used to identify spatial spillover effects and the impacts of neighbouring areas, serving as a key tool for evaluating the efficiency and driving factors of land use structure. (Luge et al., 2025). These models offer clear parameter interpretations and a solid theoretical foundation for analysing directional relationships and spillover effects. However, their reliance on linearity and global stationarity limits their capacity to capture non-linear interactions, high-order effects and complex spatial heterogeneity, and model stability can be compromised when the underlying processes are strongly nonstationary.The second category centres on geographically weighted regression (GWR) and its extensions, such as multi-scale regression methods (MGWR), which are used to address spatial non-stationarity by allowing coefficient estimates to vary across space (Wu et al., 2025). These approaches are effective for uncovering localised spatial mechanisms and scale-dependent relationships and have been used to explore the spatial heterogeneity of land-use drivers in urban-rural regions. Yet, they are less suited to handling high-dimensional variables and intricate interaction structures, and their performance often depends on subjective choices of bandwidths and kernel functions. As noted by Lessani and Li (2024), many extensions of GWR still have these limitations and thus only partially resolve the challenges of modelling complex, multi-dimensional land systems.The third category encompasses predictive models based on remote sensing and machine learning, including random forests, support vector machines, XGBoost, and deep learning. These models have demonstrated strong capabilities in extracting complex spatiotemporal patterns from large-scale remote sensing and multi-source big data, and can achieve high predictive accuracy in land-use classification, change detection and risk assessment. However, they often suffer from limited interpretability and weak connections to established theoretical frameworks in land-use and sustainability research (Argota Sánchez-Vaquerizo and Helbing, 2025). Recent advances in explainable artificial intelligence (XAI), including SHAP and partial dependence plots (PDPs), have enhanced the interpretability of such models by quantifying global and local feature contributions and interactions, leading to composite frameworks such as XGBoost-SHAP. These approaches have helped to bridge, to some extent, the gap between "spatial processes" and "black-box predictions" (Alvarez-Garcia et al., 2025;Cui et al., 2025). Nonetheless, their application in urban-rural sustainability assessment remains fragmented, and XAI tools have rarely been embedded within systematic evaluation frameworks that integrate economic, ecological and social dimensions. Overall, existing approaches either prioritise statistical inference under restrictive assumptions or emphasise predictive performance at the expense of interpretability, with few attempts to integrate their respective strengths into a coherent analytical workflow.Building on the above review, it is clear that existing research has made significant contributions to understanding the spatial patterns, structures, and efficiency of urban-rural land use, as well as the governance challenges of peri-urban transformation. However, several key gaps remain. First, at the conceptual and analytical levels, there is a lack of systematic exploration of the coupling mechanisms between land-use transitions and their impacts on economic vitality, ecological quality, and social well-being. This results in an absence of a quantitative basis for evaluating the dynamic transformation processes of "coordination-conflict" outcomes in urban-rural regions, and for identifying when development pathways remain sustainable or become problematic. Second, the non-linear threshold relationships and interaction effects among urban-rural land-use factors have not been clearly identified, making it difficult to determine how different land use structures and combinations influence sustainability outcomes, and under what critical conditions marginal changes in landuse configurations can trigger regime shifts. Third, at the methodological level, the integration of multi-source spatial data and machine learning models into urban-rural sustainability research frameworks remains underdeveloped. While single methods have been fruitfully applied, there is a lack of integrated workflows that can simultaneously capture multi-dimensional coupling, spatial heterogeneity and non-linear threshold effects, and translate these insights into policy-relevant indicators for sustainable land-use governance.In response to these gaps and the associated practical needs, this study addresses the following core research question: How do land-use transitions in evolving urban-rural systems interact and co-evolve across the economic, ecological and social dimensions, and under what critical conditions do these processes shift from coordination to conflict? To answer this question, three interrelated research objectives are proposed: (1) To develop an Urban-Rural Sustainability Index (URSI) that integrates economic, ecological, and social dimensions, thereby quantifying the multi-dimensional coupling characteristics of urban-rural sustainability; (2) To employ the CRITIC method and the Coupling Coordination Model (CCM) to characterise the spatial coordination mechanisms between human activity intensity and ecological sensitivity, and to identify the linear effects of different land use types and structures on urban-rural sustainability; (3) To develop a quantitative analytical framework for urban-rural sustainability centred on "multi-dimensional coupling-nonlinear driversthreshold identification". Building on the interpretability of traditional panel models, the framework incorporates a Random Effects Model (REM) together with an XGBoost-SHAP approach to form a composite analytical pathway that combines statistical explanation, non-linear pattern recognition and segmented effect profiling.Correspondingly, the study makes three main contributions. First, at the theoretical level, it presents an analytical framework that reveals the mechanisms of "multi-dimensional coupling and non-linear segmentation" within urban-rural systems. This framework extends existing discussions beyond single-dimensional linear effects to include cross-dimensional coupling and critical threshold mechanisms. Second, at the methodological level, it establishes a quantitative workflow that links statistical models (panel and random effects models, CCM) with machine learning models (XGBoost and SHAP), offering an operational technical route for identifying nonlinear relationships and threshold effects in complex land systems. Third, at the practical level, using Suzhou as an empirical case, the study identifies policy-relevant land use thresholds and key driving mechanisms. It provides measurable and testable evidence that supports spatial optimisation and sustainable governance in rapidly urbanising regions, with potential applications to other urban-rural contexts.Urban-rural land-use transformation is both a consequence of urbanisation and a critical driver of urban and rural development (Somanje et al., 2020). In this process, a dynamic system emerges as people, capital, resources, and land shift between urban and rural areas, with these factors over space and and et al., et al., this transformation, by rural capital, and has often urban-rural disparities by the of toward et al., 2021). et al. (2021) that sustainable urban-rural land use the spatial of capital, and development on both of the urban-rural this balance a dynamic across economic, ecological, and social dimensions, thereby gaps between urban and rural toward this it is to develop a comprehensive framework for the sustainability of land use in integrated urban and rural In this the Urban-Rural Sustainability Index (URSI) as a crucial tool for the sustainability of regional land-use The of the in this study is based on the system coupling and coordination and the framework of sustainable development This that sustainable development in urban and rural systems is the of a dynamic balance between economic vitality, ecological and social well-being, and be as a and evolving et al., 2021). These three dimensions interact and the of coordination and sustainability in regional drives growth, ecological capacity sustainable use, and social well-being of and social the coordination of these three components can sustainable urban-rural integration be et al., this theoretical this study the for the evaluation as from the Development to and The sustainable development in this is to achieve ecological and in within the framework of urban-rural This focuses not only on economic development on the of ecological and social based on the urban-rural sustainable development the is into three economic, ecological, and The economic the development dynamics and of urban and rural areas, the ecological focuses on environmental quality, and environmental the social social the of and social and from a measurable this study multi-source data indicators that the characteristics of the three dimensions to the The of indicators is by three First, the theoretical that to a and within the sustainable development Second, data the indicators are based on or multi-source data, such as of and Index This approach and spatiotemporal Third, to address the study the CRITIC method to evaluate the and of the indicators. This that in the system is and As in is to economic, ecological or social dimensions, and to the of urban-rural sustainable The economic of the the capacity for regional economic development and its on the transitions in land use between urban and rural It is including economic vitality, and and the a of indicators is by the of and and studies that such as and the of urban and rural and their to for and and and related and are of the and its potential for growth et al., 2021). such as and the economic infrastructure and which are crucial for economic integration between urban and rural areas et al., 2020). and production are the of and zones, development zones, and These indicators the of capacity and production as well as the of economic and the of a to to evolving structures and 2019). are as for and the capacity to support economic activities such as and the is by such as and by data, which an of evidence on economic et al., ecological of the sustainability of land use in of ecological and environmental governance using indicators infrastructure is by and of These include urban and which are key indicators for the of urban and its in quality, and environmental health et al., et al., areas, including and are for ecological functions and and the and Additionally, environmental such as systems, and the ecological governance capacity and its in control and These are to environmental in the of urbanisation and (Fu et al., social of encompasses three interrelated of social of governance and social and the of cultural and by indicators of is primarily in the of and which well-being and health et al., 2025). and and and the social governance capacity and the of et al., 2021). These are core of social in the of urban-rural integration et al., 2025). and cultural and and cultural and and cultural are as key indicators of the of cultural and and et al., 2021). of the and of these are used as indicators of and for These as crucial for and social as well as for cultural and on social sustainability and social highlights that these to social a of and development et al., et al., they a in the social for sustainable integration between urban and rural other studies on the sustainability of urban-rural land use, the in this research encompasses evaluation indicators across the economic, ecological, and social dimensions, which can the core mechanisms of urban-rural integration to some this assessment framework can as a systematic tool to identify the strengths and in the sustainability of urban-rural land The results from this assessment framework systematically the and functions of urban-rural areas, with decision-making support to sustainable on the of on urban-rural land-use this study a comprehensive framework that combines economic, ecological and social dimensions to evaluate the Urban-Rural Sustainability Index study Suzhou in as the research As of Suzhou and Suzhou and and with a and an urbanisation of Suzhou is a in the and one of the regions in to It has been by and spatial expansion et al., the and Suzhou has the integration of and the of development zones, leading to the of its urban functions and spatial structure. land has been into residential, industrial, and land, resulting in significant changes in and landscape patterns (Zhang et al., As a key in urban and and administrative of the study the of urbanisation the and The CRITIC method is an approach by et al. the of indicators by their and This method is particularly suited for offering a systematic approach to determine the following data and is using as indicators negative indicators of intensity the of and is as is the of of of the integrates both the and of indicators, of a of by the of are by the the assessment two remote sensing data indicators, and Index as in the of the and The Coupling Coordination Model (CCM) is to the between and that the using economic economic and social ecological and are used for coupling between and is based on coupling coupling between and a and coordination between the two systems. However, the coupling between of coupled systems and of this study the from existing et al., which is as link the Urban-Rural Sustainability Index (URSI) and its coupling coordination (CCM) with land-use characteristics in a this study a spatial panel at the of the study of Suzhou is into and for the and associated ecological and indicators for from to a several over traditional administrative First, it the which can data Second, it a of within and highlights localised a approach remains over making it for analysing dynamic land-use panel data to simultaneously for the dimensions of and this study the Random Effects Model (REM) to the between the Urban-Rural Sustainability Index and land use the Effects which that effects are the that effects are not are random variables from a This the model to for both and random making it particularly for research with or when the is to capture within and between regions form of the Random Effects Model used in this study can be the from the for in is the vector of variables for in including land-use indicators of land, and ecological, and is the is the vector of regression the marginal impact of on the the random to an heterogeneity across and is the random to to and core of the that the effects are with the this the and estimates the effects and the of both and thereby broader to urban-rural In the model are using the which provides estimates in the of and in panel to the of the is to the results from the Effects and Random Effects that the is for the data at systematically the complex, and of land-use on the Urban-Rural Sustainability Index this study employed the modelling in with to linear models, has demonstrated predictive performance by and non-linear threshold effects between variables et al., and 2025). This methodological makes it for the complex and relationships associated with the research in this an of a the the loss and the and for the at the is the of and control model complexity, thereby from its predictive this the variables of areas from land-use and other The the results based predictive performance assessed by the coefficient of and address the interpretability associated with complex machine learning models, SHAP This method from to a of into contributions et al., the SHAP for the can be the model and is the marginal of feature to the for analysing the SHAP the key global drivers of land use Additionally, SHAP dependence and interaction plots insights into the non-linear marginal effects and between different land-use study for the sustainability of urban-rural land use, including remote sensing data, the and data In this two composite and to urban-rural land-use dynamics in Suzhou during the of urban expansion from to The three economic economic activity intensity and social the ecological and ecological The characteristics of these indicators during the study are in the system, the a clear spatial in primarily in the core urban of This in to a notable with the of in regions, such as and significant However, in despite the spatial of the a This is to the impact of the with from studies on Chinese during the et al., across a structure. This the shift from a development model to a with across the a spatial expansion In the primarily the centred on Suzhou and Taken together, these indicators the and transitions across economic, social, and ecological in the for an Urban-Rural Index To determine the influence of different indicators, the CRITIC method subjective by identifying key for across the study as in the to the for over within the system, them as the most indicators within their respective dimensions. the demonstrated a the ecological from to that a of stability and urban-rural land These indicators into the Coupling Coordination Model (CCM) to the which is used to the evolving dynamics throughout the land transformation study employed the Coupling Coordination Model (CCM) to evaluate the for Suzhou from to the spatial and of urban-rural land-use in the of urban expansion classification, conflicts categorised into intensity in urban areas, including the and as well as with an expansion of to and expansion et al., and et al., 2023). Overall, the from a to pattern in Suzhou the and of critical insights into the dynamic between urban economic growth, spatial expansion and sustainable This highlights the of urban planning and ecological governance to the with the in to the As in the a of with of and a of The that there is between the and do not the that is for on this result, the model for the main analysis to its to achieve efficiency the thereby the of the effects. presents estimates for two and its change In the model the the coefficient among land-use categories that regions are associated with urban-rural This is with land and on et al., 2022). and a significant negative that agricultural and ecological are associated with of support and ecological et al., 2018). a significant negative This research the models the and of in the The and remain the of the in the remains strongly To further explore the impact of spatial heterogeneity, in and under the of Suzhou and the results are in These that urban development intensity remains the primary driver of and studies by et al. and et al. this research highlights that different types of land use, ecological and agricultural areas, a significant in These land-use categories a effect and emphasise their in both and production in the to with which highlights the of infrastructure in urban-rural sustainability and with theoretical that is significant for urban ecological (He et al., these results a driver of the and transformation, and an empirical basis for the non-linear interaction and segmented effect further and the results from the modelling and analysis employed to explore non-linear thresholds and interaction effects among different land-use the of variables and their contributions based on two model the model and the change model the plots on the the SHAP from to These plots the of land-use to the model In the SHAP plots on the the and of local impacts for The model a strong between the and the of as well as significant effects between land and other landuse The a in SHAP to which the marginal contributions beyond this The in the Taken together, these patterns an empirical threshold for planning with particularly as the the plots further a for the a of above its this level, SHAP that to urban and as the a of the that at a an effect that is in the is and with as This is with a areas to the marginal as change model that in the from the influence of land-use the of land-use and expansion remains the The SHAP dependence a response growth, with contributions being and as the growth from in either The is for expansion for the in and
Language: English
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W7129048739
Cites:
Cited by:
Related to: