Modular Deep-Learning-Based Early Warning System for Deadly Heatwave Prediction

2025-12-09

AI Summary

Predicting fatal heatwaves faces challenges including ambiguous mortality definitions, scarce historical data, and limited spatiotemporal generalizability of existing early-warning systems. To address these, we propose DeepTherm—a mortality-agnostic early-warning system based on a dual-path deep learning architecture that disentangles baseline mortality from thermal effects, enabling robust spatiotemporal forecasting of all-cause mortality risk. We introduce the first modular heatwave fatality-risk warning framework, supporting tunable trade-offs between false positives and false negatives. DeepTherm integrates heterogeneous multi-source data—including meteorological, demographic, and health indicators—via multi-task time-series modeling. Evaluated on real-world multi-regional data from Spain, the model demonstrates consistent high accuracy across diverse time periods and population subgroups. It significantly outperforms baseline methods in both lead time and robustness, establishing a new benchmark for operational heatwave mortality forecasting.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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.

Problem

• Predicts deadly heatwaves without mortality history data
• Addresses data availability and robustness for early warnings
• Balances missed and false alarm trade-offs in predictions

Innovation

• Modular deep learning system for heatwave prediction
• Dual-prediction pipeline disentangles baseline mortality
• No requirement for historical heat-related mortality data