Physics-based models outperform AI weather forecasts of record-breaking extremes
Science Advances · 01.05.2026 · 12 (18)
DOI: 10.1126/sciadv.aec1433 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 01.05.2026. Verfasst von Zhongwei Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Statistics, Karlsruhe Institute of Technology, Karlsruhe, Germany. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Swiss National Science Foundation, European Union’s Horizon 2020 research and innovation programme.
Abstract (Originalsprache)
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.
Autor:innen und Institutionen
- Institute of Statistics, Karlsruhe Institute of Technology, Karlsruhe, Germany.
- Research Institute for Statistics and Information Science, Geneva School of Economics and Management, University of Geneva, Geneva, Switzerland.
- Institute for Atmospheric and Climate Science, Department of Environmental Systems Science, ETH Zurich, Zurich, Switzerland.
- Department of Compound Environmental Risks, Helmholtz Centre for Environmental Research-UFZ, Leipzig, Germany.
- Department of Hydro Sciences, TUD Dresden University of Technology, Dresden, Germany.
- Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden/Leipzig, Germany.
ORCID-Profile: Zhongwei Zhang, Erich Fischer, Jakob Zscheischler, Sebastian Engelke
Förderung
- Swiss National Science Foundation
- European Union’s Horizon 2020 research and innovation programme
Zitieren
APA
Zhang, Z., Fischer, E., Zscheischler, J., & Engelke, S. (2026). Physics-based models outperform AI weather forecasts of record-breaking extremes. Science Advances, 12(18). https://doi.org/10.1126/sciadv.aec1433
Vancouver
Zhang Z, Fischer E, Zscheischler J, Engelke S. Physics-based models outperform AI weather forecasts of record-breaking extremes. Science Advances. 2026;12(18). doi:10.1126/sciadv.aec1433
BibTeX
@article{Zhang2026,
author = {Zhang, Zhongwei and Fischer, Erich and Zscheischler, Jakob and Engelke, Sebastian},
title = {Physics-based models outperform AI weather forecasts of record-breaking extremes},
journal = {Science Advances},
year = {2026},
volume = {12},
number = {18},
doi = {10.1126/sciadv.aec1433}
}
EUVIMED