Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling

Abstract:Observed records of climate extremes provide an incomplete view of plausible hazards, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates hazards striking multiple locations simultaneously. We introduce DeepX-GAN (Dependence-Enhanced Embedding for Physical eXtremes-Generative Adversarial Network), a deep generative model that explicitly captures the spatial structure of rare extremes. Its zero-shot generalizability enables the simulation of statistically plausible extremes beyond the observed record, evaluated against long climate model large-ensemble simulations. We define two unseen types: direct-hit extremes that affect the target, and near-miss extremes that narrowly miss. These unrealized events reveal hidden risks and can either prompt proactive adaptation or reinforce a false sense of resilience. Applying DeepX-GAN to the Middle East and North Africa shows that the probability of unseen heat extremes is disproportionately distributed toward countries with high vulnerability and low socioeconomic readiness. Using a representative climate simulation, we demonstrate how future warming could expand and shift these hazards, creating persistent hotspots in Northwest Africa and the Arabian Peninsula and new hotspots in Central Africa, necessitating spatially adaptive resilience planning.

Published in Earth's Future, DOI: https://doi.org/10.1029/2026EF008861. Please cite the published version accordingly

Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph); Data Analysis, Statistics and Probability (physics.data-an); Geophysics (physics.geo-ph); Machine Learning (stat.ML)

arXiv:2507.09211 [cs.LG]

(or arXiv:2507.09211v3 [cs.LG] for this version)

https://doi.org/10.1029/2026EF008861 DOI(s) linking to related resources