Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 55 min ago
Peer-reviewedCC BYPhysical Review Letters

AI-Boosted Rare Event Sampling to Characterize Extreme Weather

  • Amaury Lancelin1,2,3,4,5,6,7,8,9
  • Alexander Wikner10
  • Laurent Dubus6,11
  • Clément Le Priol1,2,3,4,5,7,8,9
  • Dorian S. Abbot10
  • Freddy Bouchet1,2,3,4,5,7,8,9
  • Pedram Hassanzadeh10
  • Jonathan Weare12,13
13 affiliations
  1. 1CNRS
  2. 2ENS
  3. 3IPSL
  4. 4Institut Polytechnique de Paris
  5. 5LMD
  6. 6Réseau de Transport d’Électricité (RTE)
  7. 7Sorbonne Université
  8. 8Université PSL
  9. 9École Polytechnique
  10. 10University of Chicago
  11. 11World Energy & Meteorology Council (WEMC)
  12. 12Courant Institute
  13. 13New York University
Open at sourceDOICite

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 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.

Related

  1. Towards operational data-driven regional weather forecasting: extreme-event skill and near-real-time verification with HRRRCast
    Daniel Abdi, Isidora Jankov, Vanderlei Vargas +9
    arXivPreprintCC BY 4.0Full textAtmospheric science & meteorologyarXiv
  2. Global warming and the Pacific Decadal Oscillation drive seasonally varying increases in extreme fire weather over the southwestern US
    Jiale Lou, Youngji Joh, Darri A. Stuber +2
    Communications Earth & EnvironmentPeer-reviewedCC BY-NC-ND 4.0General earth scienceNatureCrossref
  3. From extreme weather to agricultural consequences with agentic AI
    Minghan Yu, Mengyu Dai, Yixin Wen +1
    arXivPreprintarXiv licenceFull textAtmospheric science & meteorologyarXiv
  4. Building adaptive capacity of US Gulf Coast city practitioners to extreme weather events.
    Gabrielle Wong-Parodi, Natalie Herbert, Sarah J Fendrich +14
    PNAS nexusPeer-reviewedCC BYFull textClimate scienceEurope PMC
  5. A neural network-based Universal Thermal Climate Index for reliable global thermal-stress classification across extreme weather
    Bikem Pastine, Milan Klöwer, Tianning Tang +2
    arXivPreprintCC BY 4.0Full textAtmospheric science & meteorologyarXiv

Cite

BibTeXRIS
BibTeX
@article{lancelin2026aiboosted,
  title = {{AI-Boosted Rare Event Sampling to Characterize Extreme Weather}},
  author = {Amaury Lancelin and Alexander Wikner and Laurent Dubus and Clément Le Priol and Dorian S. Abbot and Freddy Bouchet and Pedram Hassanzadeh and Jonathan Weare},
  journal = {Physical Review Letters},
  year = {2026},
  month = jun,
  doi = {10.1103/b1gc-9c2q},
  url = {https://doi.org/10.1103/b1gc-9c2q},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - AI-Boosted Rare Event Sampling to Characterize Extreme Weather
AU  - Amaury Lancelin
AU  - Alexander Wikner
AU  - Laurent Dubus
AU  - Clément Le Priol
AU  - Dorian S. Abbot
AU  - Freddy Bouchet
AU  - Pedram Hassanzadeh
AU  - Jonathan Weare
PY  - 2026
DA  - 2026/06/08
JO  - Physical Review Letters
DO  - 10.1103/b1gc-9c2q
UR  - https://doi.org/10.1103/b1gc-9c2q
AB  - 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.
SN  - 0031-9007
SN  - 1079-7114
SN  - 1092-0145
ER  -