Citation

Oukawa GY, Krecl P, Targino AC. Sci. Total Environ. 2022; ePub(ePub): ePub.

Copyright

(Copyright © 2022, Elsevier Publishing)

DOI

10.1016/j.scitotenv.2021.152836

PMID

34990665

Abstract

Characterizing the spatiotemporal variability of the Urban Heat Island (UHI) and its drivers is a key step in leveraging thermal comfort to create cities that are not only healthier, but also resilient to climate change. In this study, we developed specific daytime and nighttime multiple linear regression (MLR) and random forests (RF) models to analyze and predict the spatiotemporal evolution of the Urban Heat Island intensity (UHII), using the air temperature (T(air)) as the response variable. We profited from the wealth of in situ T(air) data and a comprehensive pool of predictors variables - including land cover, population, traffic, urban geometry, weather data and atmospheric vertical indices. Cluster analysis divided the study period into three main groups, each dominated by a combination of weather systems, that in turn, influenced the onset and strength of the UHII. Anticyclonic circulations favored the emergence of the largest UHII (hourly mean of 5.06 °C), while cyclonic circulations dampened its development. The MLR models were only able to explain a modest percentage of variance (64 and 34% for daytime and nighttime, respectively), which we interpret as part of their inability to capture key factors controlling T(air). The RF models, on the other hand, performed considerably better, with explanatory power over 96% of the variance for daytime and nighttime conditions, capturing and mapping the fine-scale T(air) spatiotemporal variability in both periods and under each cluster condition. The feature importance analysis showed that the meteorological variables and the land cover were the main predictors of the T(air). Urban planners could benefit from these results, using the high-performing RF models as a robust framework for forecasting and mitigating the effects of the UHI.

Language: en

Keywords

Machine learning; Explainable artificial intelligence; Multiple linear regression; Random forests; SHAP values