Journal article · 2026 · Open access

Physics-based models outperform AI weather forecasts of record-breaking extremes

Zhongwei Zhang, Erich Markus Fischer, Jakob Zscheischler A, Sebastian Engelke

Science Advances, 12(18), eaec1433 · Published 29 April 2026 · DOI 10.1126/sciadv.aec1433

Free PDFView at the publisherCite this paper

In brief

“Physics-based models outperform AI weather forecasts of record-breaking extremes” is a 2026 journal article by Zhongwei Zhang and 3 co-authors, published in Science Advances. OpenAlex counts 60 citations as of 15 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Science Advances.

Citations
60
Most cited in
2026 (57)
Field-weighted impact
92.05
References
52
Authors
4

Abstract

Artificial intelligence (AI)-based models are revolutionizing weather forecasting and have surpassed leading numerical weather prediction systems on various benchmark tasks. However, their ability to extrapolate and reliably forecast unprecedented extreme events remains unclear. Here, we show that for record-breaking weather extremes, the physics-based numerical model High RESolution forecast (HRES) from the European Centre for Medium-Range Weather Forecasts still consistently outperforms state-of-the-art AI models GraphCast, GraphCast operational, Pangu-Weather, Pangu-Weather operational, and Fuxi. We demonstrate that forecast errors in AI models are consistently larger for record-breaking heat, cold, and wind than in HRES across nearly all lead times. We further find that the examined AI models tend to underestimate both the frequency and intensity of record-breaking events, and they underpredict hot records and overestimate cold records with growing errors for larger record exceedance. Our findings underscore the current limitations of AI weather models in extrapolating beyond their training domain and in forecasting the potentially most impactful record-breaking weather events that are particularly frequent in a rapidly warming climate. Further rigorous verification and model development is needed before these models can be solely relied upon for high-stakes applications such as early warning systems and disaster management.

Cite this paper

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

APA 7

Zhang, Z., Fischer, E. M., A, J. Z., & Engelke, S. (2026). Physics-based models outperform AI weather forecasts of record-breaking extremes. Science Advances, 12(18), eaec1433. https://doi.org/10.1126/sciadv.aec1433

MLA 9

Zhang, Zhongwei, et al. “Physics-based models outperform AI weather forecasts of record-breaking extremes.” Science Advances, vol. 12, no. 18, 2026, p. eaec1433. https://doi.org/10.1126/sciadv.aec1433.

Chicago

Zhang, Zhongwei, Erich Markus Fischer, Jakob Zscheischler A, and Sebastian Engelke. 2026. “Physics-based models outperform AI weather forecasts of record-breaking extremes.” Science Advances 12 (18): eaec1433. https://doi.org/10.1126/sciadv.aec1433.

Harvard

Zhang, Z. et al. (2026) ‘Physics-based models outperform AI weather forecasts of record-breaking extremes’, Science Advances, 12(18), p. eaec1433. doi:10.1126/sciadv.aec1433.

IEEE

Z. Zhang, E. M. Fischer, J. Z. A, and S. Engelke, “Physics-based models outperform AI weather forecasts of record-breaking extremes,” Science Advances, vol. 12, no. 18, p. eaec1433, 2026, doi: 10.1126/sciadv.aec1433.

BibTeX

@article{zhang2026physics,
  title     = {{Physics-based models outperform AI weather forecasts of record-breaking extremes}},
  author    = {Zhang, Zhongwei and Fischer, Erich Markus and A, Jakob Zscheischler and Engelke, Sebastian},
  journal   = {Science Advances},
  year      = {2026},
  volume    = {12},
  number    = {18},
  pages     = {eaec1433},
  doi       = {10.1126/sciadv.aec1433},
  url       = {https://doi.org/10.1126/sciadv.aec1433}
}

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

  • GraphCast
  • Pangu-Weather
  • Fuxi
  • heat records
  • forecast verification

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?

Zhang, Z., Fischer, E. M., A, J. Z., & Engelke, S. (2026). Physics-based models outperform AI weather forecasts of record-breaking extremes. Science Advances, 12(18), eaec1433. https://doi.org/10.1126/sciadv.aec1433

How many times has this paper been cited?

60 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 Science Advances.

Who wrote this paper?

Zhongwei Zhang, Erich Markus Fischer, Jakob Zscheischler A, Sebastian Engelke.

What is the DOI of this paper?

10.1126/sciadv.aec1433. The permanent link is https://doi.org/10.1126/sciadv.aec1433.

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.