Metraipolis › archive › dc_9ae8eaaea6de

Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes — arXiv:2610.20519

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20519
License (as archived): CC0-1.0
Archived: 2026-10-15T14:25:01.451Z
SHA-256 of the archived text: 4acf323b76e94cc1214f5eaf64779fef77b44bef7f4e4092eb9423d1e8a76a25
Stable URL of this page: https://metraipolis.com/documento/dc_9ae8eaaea6de

How to cite

Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes — arXiv:2610.20519 — arXiv (en), https://arxiv.org/abs/2610.20519 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ae8eaaea6de (Metraipolis archive dc_9ae8eaaea6de, sha256 4acf323b76e94cc1214f5eaf64779fef77b44bef7f4e4092eb9423d1e8a76a25)

BibTeX

@misc{dc9ae8eaaea6de,
  title = {Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes — arXiv:2610.20519},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20519},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ae8eaaea6de; sha256 4acf323b76e94cc1214f5eaf64779fef77b44bef7f4e4092eb9423d1e8a76a25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20519. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI weather prediction (AIWP) models have emerged as a key complement to physics-based numerical weather prediction (NWP) models, and now often outperform them on aggregate skill. Yet, several studies report that physics-based models still forecast extreme events better, in particular record-breaking extremes, based on the evaluation of deterministic forecasts. Here we evaluate heat extreme forecasts from probabilistic AIWP models over global land and show that they clearly outperform the ECMWF IFS ensemble, both raw and post-processed, including for record-breaking events, in all regions and at all lead times considered. AIWP models better forecast the occurrence and intensity of extremes, are better calibrated in the tail and miss fewer records. Station observations confirm these results. We argue that many reported AIWP limitations stem from unsuitable verification choices, specifically comparing deterministic forecasts that target different quantities. Instead, a fair evaluation of extremes necessitates probabilistic verification.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.AP, nuovi lavori del giorno).
Categorie arXiv: Applications (stat.AP) ; Geophysics (physics.geo-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.20519 — 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 2026-10-15T13:54:50.315Z dalla pagina https://arxiv.org/list/stat.AP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).