Preprint · 2026 · Open access

Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes

Jakob Benjamin Wessel, Fiona R. Spuler, Christopher A. T. Ferro, Marlene Kretschmer, Sebastian Sippel

arXiv (Cornell University) · Published 14 October 2026 · DOI 10.48550/arxiv.2610.20519

Free PDFView at the publisherCite this paper

In brief

“Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes” is a 2026 preprint by Jakob Benjamin Wessel and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
54
Authors
5

Abstract

AI weather prediction (AIWP) models have emerged as a key complement to physics-based numerical weather prediction (NWP) models, and now often outperform them on aggregate skill. Yet, several studies report that physics-based models still forecast extreme events better, in particular record-breaking extremes, based on the evaluation of deterministic forecasts. Here we evaluate heat extreme forecasts from probabilistic AIWP models over global land and show that they clearly outperform the ECMWF IFS ensemble, both raw and post-processed, including for record-breaking events, in all regions and at all lead times considered. AIWP models better forecast the occurrence and intensity of extremes, are better calibrated in the tail and miss fewer records. Station observations confirm these results. We argue that many reported AIWP limitations stem from unsuitable verification choices, specifically comparing deterministic forecasts that target different quantities. Instead, a fair evaluation of extremes necessitates probabilistic verification.

Cite this paper

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

APA 7

Wessel, J. B., Spuler, F. R., Ferro, C. A. T., Kretschmer, M., & Sippel, S. (2026). Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.20519

MLA 9

Wessel, Jakob Benjamin, et al. “Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.20519.

Chicago

Wessel, Jakob Benjamin, Fiona R. Spuler, Christopher A. T. Ferro, Marlene Kretschmer, and Sebastian Sippel. 2026. “Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.20519.

Harvard

Wessel, J. B. et al. (2026) ‘Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes’, arXiv (Cornell University). doi:10.48550/arxiv.2610.20519.

IEEE

J. B. Wessel, F. R. Spuler, C. A. T. Ferro, M. Kretschmer, and S. Sippel, “Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.20519.

BibTeX

@misc{wessel2026probabilistic,
  title     = {{Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes}},
  author    = {Wessel, Jakob Benjamin and Spuler, Fiona R. and Ferro, Christopher A. T. and Kretschmer, Marlene and Sippel, Sebastian},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.20519},
  url       = {https://doi.org/10.48550/arxiv.2610.20519}
}

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 › Meteorological Phenomena and Simulations

  • probabilistic forecasting
  • extreme heat
  • numerical weather prediction
  • forecast verification
  • probabilistic verification
  • forecast calibration
  • extreme event prediction
  • station observations

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?

Wessel, J. B., Spuler, F. R., Ferro, C. A. T., Kretschmer, M., & Sippel, S. (2026). Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.20519

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?

Jakob Benjamin Wessel, Fiona R. Spuler, Christopher A. T. Ferro, Marlene Kretschmer, Sebastian Sippel.

What is the DOI of this paper?

10.48550/arxiv.2610.20519. The permanent link is https://doi.org/10.48550/arxiv.2610.20519.

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.