Modular Deep-Learning-Based Early Warning System for Deadly Heatwave Prediction
This work addresses the problem of public health threats from severe heatwaves in urban areas by providing an early warning system, though it appears incremental as it builds on existing deep learning methods for mortality prediction.
The paper tackled the challenge of predicting deadly heatwaves without requiring historical heat-related mortality data by proposing DeepTherm, a modular deep-learning-based early warning system, and demonstrated consistent and accurate performance across diverse regions in Spain.
Severe heatwaves in urban areas significantly threaten public health, calling for establishing early warning strategies. Despite predicting occurrence of heatwaves and attributing historical mortality, predicting an incoming deadly heatwave remains a challenge due to the difficulty in defining and estimating heat-related mortality. Furthermore, establishing an early warning system imposes additional requirements, including data availability, spatial and temporal robustness, and decision costs. To address these challenges, we propose DeepTherm, a modular early warning system for deadly heatwave prediction without requiring heat-related mortality history. By highlighting the flexibility of deep learning, DeepTherm employs a dual-prediction pipeline, disentangling baseline mortality in the absence of heatwaves and other irregular events from all-cause mortality. We evaluated DeepTherm on real-world data across Spain. Results demonstrate consistent, robust, and accurate performance across diverse regions, time periods, and population groups while allowing trade-off between missed alarms and false alarms.