EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Physics‐Based Versus AI Weather Prediction Models: A Comparative Performance Assessment of Atmospheric River Prediction

Isaac W. Davis, Aneesh Subramanian, Timothy B. Higgins, Agniv Sengupta, Luca Delle Monache

Geophysical Research Letters · 28.02.2026 · 53 (4)

DOI: 10.1029/2025gl117609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 14.02.2026. Verfasst von Isaac W. Davis und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Department of Water Resources.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML) poses a potential paradigm shift in weather forecasting, but critical questions arise regarding its ability to predict high‐impact weather events. This study evaluates five state‐of‐the‐art ML models—Aurora, GraphCast, PanguWeather, FourCastNetV2, FourCastNet—in forecasting U.S. West Coast atmospheric rivers (ARs), compared to the high‐performing physics‐based European Center for Medium‐Range Weather Forecasts' high‐resolution system (HRES) model. Analysis of 152 daily forecast cycles (November 2023–March 2024) reveals significant performance differences between the systems. While ML models often show better variable‐specific root mean square error (RMSE), HRES has superior AR detection skill for the first four forecast days. PanguWeather matches HRES skill beyond day four; other ML models lag slightly. Aurora consistently exhibits the lowest AR detection performance, despite strong variable‐specific RMSE metrics, highlighting a disconnect between RMSE performance and its ability to predict AR events. These findings underscore the need for phenomenon‐specific metrics for ML‐based numerical weather prediction model assessment and operational implementation.

Förderung

  • Department of Water Resources

Zitieren

APA

Davis, I. W., Subramanian, A., Higgins, T. B., Sengupta, A., & Monache, L. D. (2026). Physics‐Based Versus AI Weather Prediction Models: A Comparative Performance Assessment of Atmospheric River Prediction. Geophysical Research Letters, 53(4). https://doi.org/10.1029/2025gl117609

Vancouver

Davis IW, Subramanian A, Higgins TB, Sengupta A, Monache LD. Physics‐Based Versus AI Weather Prediction Models: A Comparative Performance Assessment of Atmospheric River Prediction. Geophysical Research Letters. 2026;53(4). doi:10.1029/2025gl117609

BibTeX
@article{Davis2026,
  author = {Davis, Isaac W. and Subramanian, Aneesh and Higgins, Timothy B. and Sengupta, Agniv and Monache, Luca Delle},
  title = {Physics‐Based Versus AI Weather Prediction Models: A Comparative Performance Assessment of Atmospheric River Prediction},
  journal = {Geophysical Research Letters},
  year = {2026},
  volume = {53},
  number = {4},
  doi = {10.1029/2025gl117609}
}
Kostenlos starten →