{
  "abstract": "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03106",
  "author_total": 2,
  "authors": [
    {
      "name": "Chenyu Dong"
    },
    {
      "name": "Gianmarco Mengaldo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2e08ttqy7rksr.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03106",
  "fulltext_url": null,
  "id": "2e08ttqy7rksr",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03106",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.ao-ph"
    ],
    [
      "openalex",
      "1902|Meteorological Phenomena and Simulations"
    ]
  ],
  "openalex": "W7220408132",
  "pdf_url": "https://arxiv.org/pdf/2610.03106",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2e08ttqy7rksr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2610.03106",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03106"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    }
  ],
  "title": "S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales",
  "title_text": "S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:45Z",
  "url": "https://research.draconitic.com/paper/2e08ttqy7rksr",
  "venue": "arXiv",
  "versions": []
}