Metraipolis › archive › dc_2fd549275ac2

Variable Masking for Climate Emulation in ACE — arXiv:2610.21012

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21012
License (as archived)
CC0-1.0
Archived
2026-10-16T10:49:50.942Z
SHA-256 of the archived text
77fcba267e201e6709fc1d73983693e2756ccf9e148e3540c8a1c316bb130873
Stable URL of this page
https://metraipolis.com/documento/dc_2fd549275ac2

How to cite

Variable Masking for Climate Emulation in ACE — arXiv:2610.21012 — arXiv (en), https://arxiv.org/abs/2610.21012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fd549275ac2 (Metraipolis archive dc_2fd549275ac2, sha256 77fcba267e201e6709fc1d73983693e2756ccf9e148e3540c8a1c316bb130873)
BibTeX
@misc{dc2fd549275ac2,
  title = {Variable Masking for Climate Emulation in ACE — arXiv:2610.21012},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21012},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fd549275ac2; sha256 77fcba267e201e6709fc1d73983693e2756ccf9e148e3540c8a1c316bb130873},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In the recent AI Model Intercomparison Project (AIMIP) benchmark, the ACE2.1-ERA5 emulator was shown to underestimate the true near-surface warming trend both during the training period and the out-of-sample extrapolation period. In this work, we present M-ACE2S (Masked-ACE2S), a modified version of the stochastic ACE2S model, which uses variable masking during training and reduces the reliance of M-ACE2S on any single input channel. We show that M-ACE2S improves long-term near-surface air temperature prediction. We also present a novel data normalization strategy called "global mean removal", which, combined with masking, further improves the near-surface temperature forecasts. We show that M-ACE2S outperforms the ACE2S baseline on in-sample data for ERA5 while improving training stability and generalizability of near-surface temperature to unseen forcing when paired with global mean removal.

Tema degli esploratori: terra, clima ed energia (elenco arXiv physics.ao-ph, nuovi lavori del giorno).
Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.21012 — 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 2026-10-16T08:57:37.397Z dalla pagina https://arxiv.org/list/physics.ao-ph/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).