Preprint · 2026 · Open access

Weather Emulators at the Frontier of Heat Extremes Predictability

Cas Decancq, Thomas Mortier, Jessica Keune, Diego G. Miralles

arXiv (Cornell University) · Published 30 July 2026 · DOI 10.48550/arxiv.2607.28220

Open PDFView at the publisherCite this paper

In brief

“Weather Emulators at the Frontier of Heat Extremes Predictability” is a 2026 preprint by Cas Decancq and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
69
Authors
4

Abstract

Atmospheric predictability declines rapidly beyond the next ten days, such that forecasts at longer lead times primarily convey large-scale trends rather than specific states. Yet in a warming world, improving early warnings of extreme heat is an increasingly critical challenge. Here we evaluate six state-of-the-art deep learning weather emulators - Pangu-Weather, FuXi, ArchesWeather, AIFS, GraphCast and Aurora - alongside leading dynamical systems and statistical baselines in forecasting global near-surface temperature and extreme heat at lead times of 10-15 days. We find that several emulators rival or even surpass physics-based forecasts in deterministic temperature skill, but do so at the cost of reduced spectral fidelity, in a process widely known as blurring. While all models show some degree of predictive skill for extreme heat, most emulators under-represent peak intensities, and IFS recall is greater than that of any of the emulators. These results highlight both the emerging potential of AI to enhance extended range temperature prediction, and the remaining challenges in delivering reliable, actionable early warnings in a changing climate.

Cite this paper

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

APA 7

Decancq, C., Mortier, T., Keune, J., & Miralles, D. G. (2026). Weather Emulators at the Frontier of Heat Extremes Predictability. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.28220

MLA 9

Decancq, Cas, et al. “Weather Emulators at the Frontier of Heat Extremes Predictability.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2607.28220.

Chicago

Decancq, Cas, Thomas Mortier, Jessica Keune, and Diego G. Miralles. 2026. “Weather Emulators at the Frontier of Heat Extremes Predictability.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.28220.

Harvard

Decancq, C. et al. (2026) ‘Weather Emulators at the Frontier of Heat Extremes Predictability’, arXiv (Cornell University). doi:10.48550/arxiv.2607.28220.

IEEE

C. Decancq, T. Mortier, J. Keune, and D. G. Miralles, “Weather Emulators at the Frontier of Heat Extremes Predictability,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2607.28220.

BibTeX

@misc{decancq2026weather,
  title     = {{Weather Emulators at the Frontier of Heat Extremes Predictability}},
  author    = {Decancq, Cas and Mortier, Thomas and Keune, Jessica and Miralles, Diego G.},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2607.28220},
  url       = {https://doi.org/10.48550/arxiv.2607.28220}
}

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

  • extreme heat
  • extended-range forecasting
  • near-surface temperature
  • blurring
  • spectral fidelity
  • GraphCast
  • Pangu-Weather
  • Fuxi

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?

Decancq, C., Mortier, T., Keune, J., & Miralles, D. G. (2026). Weather Emulators at the Frontier of Heat Extremes Predictability. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.28220

How many times has this paper been cited?

1 times, according to OpenAlex on 20 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 at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Cas Decancq, Thomas Mortier, Jessica Keune, Diego G. Miralles.

What is the DOI of this paper?

10.48550/arxiv.2607.28220, permanently at https://doi.org/10.48550/arxiv.2607.28220. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.