Ai Wang , Daofeng Liu , Zijing Li , Shaoting Liu , Yunfei Nie , Qiang Zhang
{"title":"Spatiotemporal decoupling of land surface temperature driving mechanisms using ensemble learning","authors":"Ai Wang , Daofeng Liu , Zijing Li , Shaoting Liu , Yunfei Nie , Qiang Zhang","doi":"10.1016/j.scs.2025.106868","DOIUrl":null,"url":null,"abstract":"<div><div>As urbanization accelerates and the impacts of climate change become increasingly evident, understanding the nonlinear response mechanisms of land surface temperature (LST) in urban environments, along with its spatiotemporal non-stationarity, has become a significant focus in urban climatology. Using Hefei City as a case study, this research integrates multisource remote sensing data from 2002, 2013, and 2022 with a Geographically and Temporally Weighted Random Forest and SHAP ensemble framework (GTWRF-SHAP) to systematically identify the multidimensional driving mechanisms of LST across different stages of urban development. The results show that the LST distribution in Hefei has evolved from a “single-core concentration” to a “multi-core dispersion” pattern. High-temperature areas have expanded from the central urban area to emerging districts, such as the Economic and Technological Development Zone and the High-Tech Zone, while low-temperature areas remain concentrated around ecological nodes like reservoirs and forest parks, exhibiting a spatial evolution characterized by “heat island expansion and cold source retention.” With ongoing urbanization, the primary drivers of LST have significantly shifted from being predominantly natural factors to a synergy of natural, built environment, and socio-economic factors. Nonetheless, natural factors continue to play a crucial role in the cooling effects at local ecological nodes. The study further reveals significant nonlinear effects and spatiotemporal heterogeneity in key driving factors, particularly the threshold effects of factors such as vegetation cover, building height, and floor area ratio. Spatially, the cooling effect of natural factors has contracted toward the urban periphery, while the warming effect of the built environment has concentrated in the core areas, aligning closely with the city’s functional zoning and development stages. This research enhances the understanding of the driving mechanisms of LST under urbanization and provides essential scientific evidence for climate-adaptive urban planning.</div></div>","PeriodicalId":48659,"journal":{"name":"Sustainable Cities and Society","volume":"133 ","pages":"Article 106868"},"PeriodicalIF":12.0000,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Cities and Society","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2210670725007413","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
As urbanization accelerates and the impacts of climate change become increasingly evident, understanding the nonlinear response mechanisms of land surface temperature (LST) in urban environments, along with its spatiotemporal non-stationarity, has become a significant focus in urban climatology. Using Hefei City as a case study, this research integrates multisource remote sensing data from 2002, 2013, and 2022 with a Geographically and Temporally Weighted Random Forest and SHAP ensemble framework (GTWRF-SHAP) to systematically identify the multidimensional driving mechanisms of LST across different stages of urban development. The results show that the LST distribution in Hefei has evolved from a “single-core concentration” to a “multi-core dispersion” pattern. High-temperature areas have expanded from the central urban area to emerging districts, such as the Economic and Technological Development Zone and the High-Tech Zone, while low-temperature areas remain concentrated around ecological nodes like reservoirs and forest parks, exhibiting a spatial evolution characterized by “heat island expansion and cold source retention.” With ongoing urbanization, the primary drivers of LST have significantly shifted from being predominantly natural factors to a synergy of natural, built environment, and socio-economic factors. Nonetheless, natural factors continue to play a crucial role in the cooling effects at local ecological nodes. The study further reveals significant nonlinear effects and spatiotemporal heterogeneity in key driving factors, particularly the threshold effects of factors such as vegetation cover, building height, and floor area ratio. Spatially, the cooling effect of natural factors has contracted toward the urban periphery, while the warming effect of the built environment has concentrated in the core areas, aligning closely with the city’s functional zoning and development stages. This research enhances the understanding of the driving mechanisms of LST under urbanization and provides essential scientific evidence for climate-adaptive urban planning.
期刊介绍:
Sustainable Cities and Society (SCS) is an international journal that focuses on fundamental and applied research to promote environmentally sustainable and socially resilient cities. The journal welcomes cross-cutting, multi-disciplinary research in various areas, including:
1. Smart cities and resilient environments;
2. Alternative/clean energy sources, energy distribution, distributed energy generation, and energy demand reduction/management;
3. Monitoring and improving air quality in built environment and cities (e.g., healthy built environment and air quality management);
4. Energy efficient, low/zero carbon, and green buildings/communities;
5. Climate change mitigation and adaptation in urban environments;
6. Green infrastructure and BMPs;
7. Environmental Footprint accounting and management;
8. Urban agriculture and forestry;
9. ICT, smart grid and intelligent infrastructure;
10. Urban design/planning, regulations, legislation, certification, economics, and policy;
11. Social aspects, impacts and resiliency of cities;
12. Behavior monitoring, analysis and change within urban communities;
13. Health monitoring and improvement;
14. Nexus issues related to sustainable cities and societies;
15. Smart city governance;
16. Decision Support Systems for trade-off and uncertainty analysis for improved management of cities and society;
17. Big data, machine learning, and artificial intelligence applications and case studies;
18. Critical infrastructure protection, including security, privacy, forensics, and reliability issues of cyber-physical systems.
19. Water footprint reduction and urban water distribution, harvesting, treatment, reuse and management;
20. Waste reduction and recycling;
21. Wastewater collection, treatment and recycling;
22. Smart, clean and healthy transportation systems and infrastructure;