Metraipolis › archive › dc_a950c5af8c4e

EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching — arXiv:2610.09715

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09715
License (as archived)
CC0-1.0
Archived
2026-10-08T11:59:03.967Z
SHA-256 of the archived text
15ab278cfb6d2ba2528aa3e2284d784e56876ace5f7cbb1b4367ae3d93b7636e
Stable URL of this page
https://metraipolis.com/documento/dc_a950c5af8c4e

How to cite

EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching — arXiv:2610.09715 — arXiv (en), https://arxiv.org/abs/2610.09715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a950c5af8c4e (Metraipolis archive dc_a950c5af8c4e, sha256 15ab278cfb6d2ba2528aa3e2284d784e56876ace5f7cbb1b4367ae3d93b7636e)
BibTeX
@misc{dca950c5af8c4e,
  title = {EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching — arXiv:2610.09715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a950c5af8c4e; sha256 15ab278cfb6d2ba2528aa3e2284d784e56876ace5f7cbb1b4367ae3d93b7636e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce EC-EarthFlow, a generative flow matching model that emulates simulations from the physical climate model EC-Earth3. The model is trained on transient simulations from EC-Earth3 (1950-2166, SSP2-4.5) to predict the day ahead temperature field from the previous days temperature as well as annual mean temperature. Predictions are made auto-regressively with rollout periods of between a month and an extended season. Using only this variable of interest, we are able to reproduce the daily variability, spatial patterns, annual cycle and long-term trend from EC-Earth3 at a substantially lower computational cost than the physical model. We demonstrate that EC-EarthFlow is stable for long inference periods, and that it can learn the physical relationships as simulated in EC-Earth3.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Atmospheric and Oceanic Physics (physics.ao-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.09715 — 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 2026-10-08T10:50:37.710Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).