Quantifying blue–green space degradation dynamics and associated thermal responses across urban expansion patterns: Insights from interpretable machine learning

Urban expansion areas have emerged as critical hotspots of blue–green space degradation and thermal intensification during rapid urbanization. However, nonlinear relationships between multidimensional blue–green space degradation and thermal intensification, including their variation across expansion patterns, remain insufficiently understood. Using 26 cities in the Yangtze River Delta Urban Agglomeration, this study characterizes urban-expansion-area blue–green spaces (UEBGSs) and their degradation from 2000 to 2020, while identifying urban expansion patterns (UEPs). By integrating TabPFN with SHAP, the study reveals nonlinear relationships between UEBGS degradation and changes in relative land surface temperature (ΔrLST), as well as pattern-specific heterogeneity. The results indicate that: (1) edge-expansion was the dominant UEP in the Yangtze River Delta, with the intensity and pathways of UEBGS degradation varying across UEPs; (2) UEBGS degradation exhibited nonlinear relationships with ΔrLST, where green-space quantity loss and biophysical-condition degradation were the dominant contributors to thermal intensification, while structural degradation played a significant role at the early stage; and (3) the relative importance of degradation indicators, sensitive response intervals, and marginal effects differed among UEPs. Specifically, edge-expansion was more sensitive to quantity degradation, infilling-expansion responded more strongly to biophysical-condition degradation, and outlying-expansion showed buffering effects at low levels of degradation but accelerated thermal intensification at higher levels. Overall, the UEBGS degradation–ΔrLST relationship is strongly pattern-dependent, with distinct response intensities and sensitive intervals across UEPs. This finding underscores the need for pattern-specific blue–green space interventions across UEPs. This study provides a framework for understanding heat-risk formation and supports targeted thermal governance in rapidly urbanizing regions.

Authors

Institutions

Publication Details

Journal
Ecological Indicators
Published
2026-10-27
DOI
https://doi.org/10.1016/j.ecolind.2026.115763
Primary Topic
Urban Heat Island Mitigation
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Quantifying blue–green space degradation dynamics and associated thermal responses across urban expansion patterns: Insights from interpretable machine learning

Yunlu Zhang, Xueliang Yang, Xiaohan GU, Kaiyi Shi et al.
2 links
Ecological Indicators
Urban Heat Island Mitigation
article

Quantifying blue–green space degradation dynamics and associated thermal responses across urban expansion patterns: Insights from interpretable machine learning

Yunlu Zhang, Xueliang Yang, Xiaohan GU, Kaiyi Shi, Chen Chen, Yunyu Ge
article en

Abstract

Urban expansion areas have emerged as critical hotspots of blue–green space degradation and thermal intensification during rapid urbanization. However, nonlinear relationships between multidimensional blue–green space degradation and thermal intensification, including their variation across expansion patterns, remain insufficiently understood. Using 26 cities in the Yangtze River Delta Urban Agglomeration, this study characterizes urban-expansion-area blue–green spaces (UEBGSs) and their degradation from 2000 to 2020, while identifying urban expansion patterns (UEPs). By integrating TabPFN with SHAP, the study reveals nonlinear relationships between UEBGS degradation and changes in relative land surface temperature (ΔrLST), as well as pattern-specific heterogeneity. The results indicate that: (1) edge-expansion was the dominant UEP in the Yangtze River Delta, with the intensity and pathways of UEBGS degradation varying across UEPs; (2) UEBGS degradation exhibited nonlinear relationships with ΔrLST, where green-space quantity loss and biophysical-condition degradation were the dominant contributors to thermal intensification, while structural degradation played a significant role at the early stage; and (3) the relative importance of degradation indicators, sensitive response intervals, and marginal effects differed among UEPs. Specifically, edge-expansion was more sensitive to quantity degradation, infilling-expansion responded more strongly to biophysical-condition degradation, and outlying-expansion showed buffering effects at low levels of degradation but accelerated thermal intensification at higher levels. Overall, the UEBGS degradation–ΔrLST relationship is strongly pattern-dependent, with distinct response intensities and sensitive intervals across UEPs. This finding underscores the need for pattern-specific blue–green space interventions across UEPs. This study provides a framework for understanding heat-risk formation and supports targeted thermal governance in rapidly urbanizing regions.

Ecological IndicatorsVol. 192
China University of Petroleum, Beijing (CN), Beijing Forestry University (CN)
National Natural Science Foundation of China
Sustainable cities and communities, Life on land
Openalex Percentile: Top 22%
Urban Heat Island Mitigation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon