Volume 60

Heterogeneous effects of anthropogenic heat on urban thermal environment: An interpretable ML approach Yonghang Xie, Cheng Fan, Yutian Lei, Jiena Cai

Abstract

In high-density cities, anthropogenic heat (AH) emissions are an important factor affecting the urban heat island effect. Especially in summer, the heat stress on the outdoor thermal environment caused by AH emissions cannot be ignored. Due to the oversimplification of AH emissions in previous studies, the spatial differences in the role of different types of AH emissions in the urban thermal environment are not well understood. Therefore, this study proposes an interpretable machine learning framework to model and predict AH emissions and their thermal impacts in dense urban areas, with a focus on quantifying the differential responses of land surface temperature (LST) to sector-specific AH emissions (e.g., buildings, industry, transportation). The results demonstrate that the ExtraTreesRegressor model achieves optimal performance, with a coefficient of determination (R²) of 0.8. The Shap analysis reveals that, among the seven types of selected urban factors, NDVI, Building-related AH, and Industry-related AH are the key driving factors of LST across Shenzhen, China. Sensitivity experiments demonstrate that any reduction in the AHE intensity results in a corresponding decrease in the spatially averaged LST. Under an 80% reduction in AHE, the mean LST in Shenzhen decreased by 0.57°C (buildings), 0.46°C (industry), and 0.23°C (transportation). Furthermore, the cooling response to AH reduction varied spatially across Shenzhen. A reduction in building or industry-related AH emissions induced significant cooling areas in inland districts, including Guangming, Longhua, Pingshan, and parts of Futian. In contrast, coastal districts such as Nanshan and Futian exhibited more pronounced cooling effects when transportation-related AH emissions were reduced. This study elucidates the mechanistic response of urban thermal environments to spatially heterogeneous and source-specific AH emissions,providing novel insights and a theoretical foundation for developing targeted urban heat mitigation strategies.

Keywords anthropogenic heat emission, urban heat island, interpretable ML approach, sensitive analysis, urban heat mitigation