Urbanization Doubles Future Compound Heatwave Risk in the Yangtze River Delta Urban Agglomeration Based on a Machine Learning‐Statistical Hybrid Framework

Urbanization intensifies compound heatwaves (CoHot) involving concurrent hot days and nights, yet coarse‐resolution climate projections cannot resolve urban‐scale processes. Dynamical downscaling can bridge this gap but requires substantial computing for long‐term projections. Here we introduce a novel and efficient hybrid framework combining daily‐scale stacking ensemble machine learning with monthly‐scale quantile mapping to downscale CMIP6 projections to urban resolution. Applied to China's Yangtze River Delta (YRD), a highly developed urban area, this framework improves simulation of CoHot frequency, duration, and intensity, increasing spatial correlation from −0.26–0.50 to 0.29–0.77 and reducing RMSE by 18%. High‐resolution (5‐km) projections reveal cities as evolving CoHot hotspots, where urban expansion drives shifting spatial patterns. By 2050, city centers could experience about four CoHot events and over 20 CoHot days annually, with total duration twice that in surrounding rural areas. This scalable, efficient tool aids urban heat risk assessment with broad applicability to rapidly urbanizing regions worldwide.

Authors

Institutions

Publication Details

Journal
Geophysical Research Letters
Published
2026-11-20
DOI
https://doi.org/10.1029/2026gl123497
Primary Topic
Climate variability and models
Type
article
Field-Weighted Citation Impact
0.00

Funders

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

Urbanization Doubles Future Compound Heatwave Risk in the Yangtze River Delta Urban Agglomeration Based on a Machine Learning‐Statistical Hybrid Framework

Peng Ji, Chunhui Lu, Qibo Xu, Shanshui Yuan et al.
1 links
Geophysical Research Letters
Climate variability and models
article

Urbanization Doubles Future Compound Heatwave Risk in the Yangtze River Delta Urban Agglomeration Based on a Machine Learning‐Statistical Hybrid Framework

Peng Ji, Chunhui Lu, Qibo Xu, Shanshui Yuan, Junliang Jin, Sisi Chen
article en

Abstract

Urbanization intensifies compound heatwaves (CoHot) involving concurrent hot days and nights, yet coarse‐resolution climate projections cannot resolve urban‐scale processes. Dynamical downscaling can bridge this gap but requires substantial computing for long‐term projections. Here we introduce a novel and efficient hybrid framework combining daily‐scale stacking ensemble machine learning with monthly‐scale quantile mapping to downscale CMIP6 projections to urban resolution. Applied to China's Yangtze River Delta (YRD), a highly developed urban area, this framework improves simulation of CoHot frequency, duration, and intensity, increasing spatial correlation from −0.26–0.50 to 0.29–0.77 and reducing RMSE by 18%. High‐resolution (5‐km) projections reveal cities as evolving CoHot hotspots, where urban expansion drives shifting spatial patterns. By 2050, city centers could experience about four CoHot events and over 20 CoHot days annually, with total duration twice that in surrounding rural areas. This scalable, efficient tool aids urban heat risk assessment with broad applicability to rapidly urbanizing regions worldwide.

Geophysical Research LettersVol. 53(22)
California NanoSystems Institute (US), University of California, Los Angeles (US), Hohai University (CN), Nanjing University of Information Science and Technology (CN)
National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities
Sustainable cities and communities, Climate action
Climate variability and models
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
Urbanization Doubles Future Compound Heatwave Risk in the Yangtze River Delta Urban Agglomeration Based on a Machine Learning‐Statistical Hybrid Framework — Peng Ji, Chunhui Lu, et al. · Geophysical Research Letters (2026) | TGRS Research Map | TGRS