Metraipolis › archive › dc_3a0338effb72

S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales — arXiv:2610.03106

Source
arXiv
Original
https://arxiv.org/abs/2610.03106
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:28.142Z
SHA-256 of the archived text
f3864032c8643982466022153708a6842db2fe31b6a0df0c26e5b704b0fe1f86
Stable URL of this page
https://metraipolis.com/documento/dc_3a0338effb72

How to cite

S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales — arXiv:2610.03106 — arXiv, https://arxiv.org/abs/2610.03106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a0338effb72 (Metraipolis archive dc_3a0338effb72, sha256 f3864032c8643982466022153708a6842db2fe31b6a0df0c26e5b704b0fe1f86)
BibTeX
@misc{dc3a0338effb72,
  title = {S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales — arXiv:2610.03106},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03106},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a0338effb72; sha256 f3864032c8643982466022153708a6842db2fe31b6a0df0c26e5b704b0fe1f86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The subseasonal-to-seasonal (S2S) timescale, roughly from two weeks to two months ahead, is a critical forecast window for sectors such as agriculture, energy, and water management. Yet, it is widely known as the `predictability desert'. Recent AI weather models excel up to two weeks ahead but deteriorate beyond, largely because they are trained to predict fine-scale details that are neither predictable nor essential at S2S timescales. We argue that a more physically grounded objective is to forecast only the slowly varying components that remain predictable. Computer vision reached the same conclusion with the Joint-Embedding Predictive Architecture (JEPA), which predicts in latent space, discarding unpredictable details. In this work, we introduce S2S-JEPA, which brings the JEPA paradigm to S2S forecasting. It is tailored to this task through design elements from state-of-the-art AI weather models. S2S-JEPA achieves comparable skill to the gold-standard ECMWF physics-based ensemble and surpasses it on multiple metrics at weeks 5 to 6.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03106 — 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 2026-10-05T22:45:55.830Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).