.png){kind=icon}
.png){kind=icon}
Return
Assessing urban radiative cooling potential with physical and machine learning models
.png){kind=icon}
PRE
AI
X
C
Z
J
K
S
沈
H
DOI：10.1007/s12273-026-1475-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Rapid urbanization has exacerbated the urban heat island effect, significantly increasing cooling energy demand. Daytime radiative cooling (RC) offers a promising zero-energy passive cooling strategy; however, urban-scale evaluations of RC potential and the specific influence of urban morphology remain scarce. This study integrates a physical RC model with the local climate zone (LCZ) framework to simulate 10,549 buildings across 85 LCZ models in Shenzhen, China. To improve spatial generalization, we developed rapid machine learning assessment models evaluated via 5-fold spatial cross-validation. Additionally, ensemble SHapley Additive exPlanations (SHAP) analysis was utilized to quantify the impacts of meteorological and morphological parameters. The results demonstrate that CatBoost and XGBoost are the optimal algorithms for predicting roof and facade RC energy savings, achieving average test-set R2 values of 0.888 and 0.854, respectively. SHAP analysis revealed that meteorological conditions (primarily solar irradiance and wind speed) dictate performance, contributing 66.0% and 65.1% to roof and facade RC. Urban morphology acts as a major constraint; specifically, compact high-rise zones severely hinder facade cooling potential due to mutual shading. Finally, the annual theoretical RC energy-saving potential for roofs and facades in Shenzhen is estimated at 372.9 GWh and 446.8 GWh, respectively. Combined, this 819.8 GWh capacity could offset approximately 0.833% of the city’s 2019 total electricity consumption. This research provides urban planners with quantitative, transferable insights for mitigating energy demands in the built environment.
Keywords:
urban radiative cooling potential
hourly RC energy savings
local climate zone
urban morphology
machine learning
Journal
IF:
5.9
Papers:
1.5K
Citations:
4.5K
Organization
Cited Papers