Metraipolis › archive › dc_9ffe6e2da560
Do AI weather models miss extremes? — arXiv:2608.09972
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09972
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:48.812Z
- SHA-256 of the archived text
a45097cc0c70a2da8fb4fd993ab85b8d6bc5aa443e1ffd24e86f1e0499156044- Stable URL of this page
https://metraipolis.com/documento/dc_9ffe6e2da560
How to cite
Do AI weather models miss extremes? — arXiv:2608.09972 — arXiv (en), https://arxiv.org/abs/2608.09972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ffe6e2da560 (Metraipolis archive dc_9ffe6e2da560, sha256 a45097cc0c70a2da8fb4fd993ab85b8d6bc5aa443e1ffd24e86f1e0499156044)
BibTeX
@misc{dc9ffe6e2da560,
title = {Do AI weather models miss extremes? — arXiv:2608.09972},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09972},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ffe6e2da560; sha256 a45097cc0c70a2da8fb4fd993ab85b8d6bc5aa443e1ffd24e86f1e0499156044},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI weather models are often reported to underestimate extremes, but most evidence concerns deterministic regression models verified against reanalysis. We evaluate twelve physical and AI forecast models against ECMWF IFS using ten months of European station observations. The evaluation covers 10 m wind, 2 m temperature, solar radiation, and precipitation within regimes defined from a fixed ERA5 1991-2020 climatology. We find no uniform AI-specific deficit in the tails. Several AI models remain more accurate than IFS under extreme conditions, while others deteriorate markedly; comparable variation occurs among physical models. Every model nevertheless exhibits a common conditional-error pattern, overpredicting low observations and underpredicting high observations. Attenuation of extreme values therefore does not imply a uniform loss of relative skill: tail performance depends on the model, variable, and evaluation setting rather than on whether the forecast is produced by AI or physical numerical modelling. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.09972 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:57:28.323Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).