Preprint · 2026 · Open access

Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones

Nathan Chalumeau, Xavier Renard, Rémi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki, Emmanuel de Bezenac

arXiv (Cornell University) · Published 15 October 2026 · DOI 10.48550/arxiv.2610.22077

Free PDFView at the publisherCite this paper

In brief

“Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones” is a 2026 preprint by Nathan Chalumeau and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
19
Authors
6

Abstract

Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computational cost. Yet, whether this success extends to extreme events remains contested. Earlier evaluations have exposed important shortcomings, but have largely focused on deterministic models and metrics, leaving the capabilities of the latest probabilistic models less understood. We conduct an extensive benchmark of tropical cyclone forecasting, comparing GenCast, FourCastNet 3, and FGN with ECMWF's operational physics-based ensemble, IFS-ENS. We develop a suite of probabilistic metrics and diagnostic analyses to assess cyclone tracking, intensity biases, uncertainty, and the wind-pressure relationship that characterizes storm structure. We find that, despite remaining limitations in intensity and ensemble spread, leading AI models substantially outperform IFS-ENS in cyclone tracking: FGN achieves better probabilistic location scores for 90% of evaluated storms in 2025. Further analyses reveal model-specific failure modes and suggest a lingering influence of pretraining data, pointing to opportunities for targeted improvement. Nonetheless, these results suggest that AI models are capable of capturing physical relationships that remain predictive well beyond typical weather conditions, motivating further investigation into how these capabilities emerge and how to strengthen them.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Chalumeau, N., Renard, X., Meynadier, R., Rakotoarimanga, H., Detyniecki, M., & de Bezenac, E. (2026). Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.22077

MLA 9

Chalumeau, Nathan, et al. “Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.22077.

Chicago

Chalumeau, Nathan, Xavier Renard, Rémi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki, and Emmanuel de Bezenac. 2026. “Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.22077.

Harvard

Chalumeau, N. et al. (2026) ‘Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones’, arXiv (Cornell University). doi:10.48550/arxiv.2610.22077.

IEEE

N. Chalumeau, X. Renard, R. Meynadier, H. Rakotoarimanga, M. Detyniecki, and E. de Bezenac, “Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.22077.

BibTeX

@misc{chalumeau2026forecast,
  title     = {{Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones}},
  author    = {Chalumeau, Nathan and Renard, Xavier and Meynadier, Rémi and Rakotoarimanga, Hugo and Detyniecki, Marcin and de Bezenac, Emmanuel},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.22077},
  url       = {https://doi.org/10.48550/arxiv.2610.22077}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Tropical and Extratropical Cyclones Research

  • tropical cyclone forecasting
  • FourCastNet
  • cyclone tracking
  • uncertainty quantification
  • wind-pressure relationship
  • probabilistic metrics
  • extreme weather events

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Chalumeau, N., Renard, X., Meynadier, R., Rakotoarimanga, H., Detyniecki, M., & de Bezenac, E. (2026). Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.22077

How many times has this paper been cited?

0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Nathan Chalumeau, Xavier Renard, Rémi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki, Emmanuel de Bezenac.

What is the DOI of this paper?

10.48550/arxiv.2610.22077. The permanent link is https://doi.org/10.48550/arxiv.2610.22077.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.