{
  "abstract": "Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for subseasonal-to-seasonal (S2S) applications where long lead-times and domain-driven calibration are essential. To address this, we introduce Swift, a single-step consistency model that, for the first time, enables autoregressive finetuning of a probability flow model with a continuous ranked probability score (CRPS) objective. This eliminates the need for multi-model ensembling or parameter perturbations. Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running $39\\times$ faster than state-of-the-art diffusion baselines while achieving forecast skill competitive with the numerical-based, operational IFS ENS. This marks a step toward efficient and reliable ensemble forecasting from medium-range to seasonal-scales.",
  "abstract_shown": true,
  "affiliations": [
    "Argonne National Laboratory",
    "Allen Institute for AI"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jonathan G. Stock",
      "orcid": "0009-0006-2354-2373"
    },
    {
      "affs": [
        1,
        0
      ],
      "name": "Troy Arcomano",
      "orcid": "0000-0002-9359-6020"
    },
    {
      "affs": [
        0
      ],
      "name": "Veerabhadra Rao Kotamarthi",
      "orcid": "0000-0002-2612-7590"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dje3dsaj2hgjh.bib",
  "cited_by": 15,
  "doi": "10.1088/3049-4753/ae802a",
  "fulltext_url": null,
  "id": "dje3dsaj2hgjh",
  "issns": [
    "3049-4753"
  ],
  "landing_url": "https://doi.org/10.1088/3049-4753/ae802a",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1902|Meteorological Phenomena and Simulations"
    ]
  ],
  "openalex": "W7165531483",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dje3dsaj2hgjh.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T13:20:53Z",
      "native_id": "W7165531483",
      "source": "openalex",
      "url": "https://doi.org/10.1088/3049-4753/ae802a"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:1902|Meteorological Phenomena and Simulations",
      "subfield": "atmospheric"
    }
  ],
  "title": "Swift: an autoregressive consistency model for efficient weather forecasting",
  "title_text": "Swift: an autoregressive consistency model for efficient weather forecasting",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:19Z",
  "url": "https://research.draconitic.com/paper/dje3dsaj2hgjh",
  "venue": "Machine Learning Earth",
  "versions": []
}