{"ID":2847371,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27066","arxiv_id":"2510.27066","title":"AI-boosted rare event sampling to characterize extreme weather","abstract":"Weather extremes pose major societal risks, especially in a changing climate, but due to their rarity, they are difficult to study using limited observations or complex climate models. We introduce AI+RES, a framework coupling fast AI weather forecasts with a high-fidelity physics model using a rare-event algorithm to efficiently characterize extremes. This approach enables the study of the statistics and physics of very rare events, such as once per millennium heatwaves at two orders-of-magnitude lower computational cost. AI+RES can be applied broadly across climate science and other fields concerned with rare events.","short_abstract":"Weather extremes pose major societal risks, especially in a changing climate, but due to their rarity, they are difficult to study using limited observations or complex climate models. We introduce AI+RES, a framework coupling fast AI weather forecasts with a high-fidelity physics model using a rare-event algorithm to...","url_abs":"https://arxiv.org/abs/2510.27066","url_pdf":"https://arxiv.org/pdf/2510.27066v2","authors":"[\"Amaury Lancelin\",\"Alex Wikner\",\"Laurent Dubus\",\"Clément Le Priol\",\"Dorian S. Abbot\",\"Freddy Bouchet\",\"Pedram Hassanzadeh\",\"Jonathan Weare\"]","published":"2025-10-31T00:33:30Z","proceeding":"physics.ao-ph","tasks":"[\"physics.ao-ph\",\"stat.CO\",\"stat.ML\"]","methods":"[]","has_code":false}