A novel “WRF+AutoML” framework for enhanced heat estimation in urban environments

Heat stress significantly impacts public health and urban sustainability, necessitating accurate and efficient assessment methods. Numerical models are commonly used to simulate key variables such as temperature, wind speed, and humidity for calculating heat stress indices. However, their accuracy is often hindered by uncertainties of various sources. This study developed a novel, high accuracy framework that integrates the Weather Research and Forecasting (WRF) model with Automated Machine Learning (AutoML), henceforth referred to as the “WRF+AutoML” framework, to enhance heat stress estimation. Five heat stress indices derived from air temperature, wind speed, and relative humidity were evaluated within this framework, addressing three critical questions: (1) Which Machine Learning (ML) method provides the best balance of accuracy and ease of use in this framework? (2) Is it more effective to estimate heat stress directly or indirectly via related basic variables? (3) How can the number of features in the framework be reduced to create a lightweight model? The results show that Automated Machine Learning method achieves high accuracy without the need for hyperparameter tuning. Direct heat stress estimation using the“WRF+AutoML” framework significantly reduces RMSE by 67.3 %–82.6 % and MAE by 70.0 %–81.6 % compared to traditional WRF simulations, outperforming indirect estimation based on basic variables produced by the “WRF+AutoML” framework. Additionally, Both SHAP (SHapley Additive exPlanations model)-based and feature-importance-based feature selection methods effectively minimize the number of features while preserving model performance. This framework notably improves the accuracy of heat stress estimations, particularly in capturing diurnal peak variations, providing a reliable tool for heat stress risk assessment and urban heat management.