AI-Boosted Rare Event Sampling to Characterize Extreme Weather
Physical Review Letters · 05.08.2026 · 137 (6)
DOI: 10.1103/b1gc-9c2q ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Letters, online erschienen am 05.08.2026. Verfasst von Amaury Lancelin und 7 weiteren Autor:innen. Beteiligte Einrichtung: Sorbonne Université, Institut Polytechnique de Paris, École Polytechnique, Université PSL, ENS, CNRS, LMD, /IPSL, Paris, France. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Association Nationale de la Recherche et de la Technologie, National Science Foundation, University of Chicago.
Abstract (Originalsprache)
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 heat waves at two orders-of-magnitude lower computational cost. AI + RES can be applied broadly across climate science and other fields concerned with rare events.
Autor:innen und Institutionen
- Sorbonne Université, Institut Polytechnique de Paris, École Polytechnique, Université PSL, ENS, CNRS, LMD, /IPSL, Paris, France.
- Réseau de Transport d'Électricité (RTE), Paris, France.
- University of Chicago, Department of the Geophysical Sciences, Chicago, Illinois, USA.
- World Energy & Meteorology Council (WEMC), Norwich, United Kingdom.
- New York University, Courant Institute, New York, New York, USA.
Förderung
- Association Nationale de la Recherche et de la Technologie
- National Science Foundation
- University of Chicago
- National Center for Atmospheric Research
- Grand Équipement National De Calcul Intensif
- RTE France
- France-Chicago Center FACCT
- Institut des Mathématiques pour la Planète Terre
Zitieren
APA
Lancelin, A., Wikner, A., Dubus, L., Le Priol, C., Abbot, D. S., Bouchet, F., Hassanzadeh, P., & Weare, J. (2026). AI-Boosted Rare Event Sampling to Characterize Extreme Weather. Physical Review Letters, 137(6). https://doi.org/10.1103/b1gc-9c2q
Vancouver
Lancelin A, Wikner A, Dubus L, Le Priol C, Abbot DS, Bouchet F, et al. AI-Boosted Rare Event Sampling to Characterize Extreme Weather. Physical Review Letters. 2026;137(6). doi:10.1103/b1gc-9c2q
BibTeX
@article{Lancelin2026,
author = {Lancelin, Amaury and Wikner, Alexander and Dubus, Laurent and Le Priol, Clément and Abbot, Dorian S and Bouchet, Freddy and Hassanzadeh, Pedram and Weare, Jonathan},
title = {AI-Boosted Rare Event Sampling to Characterize Extreme Weather},
journal = {Physical Review Letters},
year = {2026},
volume = {137},
number = {6},
doi = {10.1103/b1gc-9c2q}
}
EUVIMED