Numerical models outperform AI weather forecasts of record-breaking extremes

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Zhongwei, Fischer, Erich, Zscheischler, Jakob, Engelke, Sebastian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909747846840320
author Zhang, Zhongwei
Fischer, Erich
Zscheischler, Jakob
Engelke, Sebastian
author_facet Zhang, Zhongwei
Fischer, Erich
Zscheischler, Jakob
Engelke, Sebastian
contents 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 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Numerical models outperform AI weather forecasts of record-breaking extremes
Zhang, Zhongwei
Fischer, Erich
Zscheischler, Jakob
Engelke, Sebastian
Atmospheric and Oceanic Physics
Artificial Intelligence
Applications
J.2; I.6.4
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 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.
title Numerical models outperform AI weather forecasts of record-breaking extremes
topic Atmospheric and Oceanic Physics
Artificial Intelligence
Applications
J.2; I.6.4
url https://arxiv.org/abs/2508.15724