{
  "abstract": "We present BEAST, the first-ever Bayesian Swin Transformer for atmospheric forecasting on 0.25$^\\circ$ global resolution able to accurately quantify both aleatoric and epistemic uncertainty. To overcome the associated computational bottlenecks, we devise an orthogonal 4D-parallelization scheme that introduces a unique domain-tensor-parallelism strategy and a novel uncertainty parallel method, enabling us to fully leverage GPU capacity and efficiently scale model training. For a 2.4-billion-parameter model, we achieve a peak performance of 3.96 EFLOP/s on 20,480 NVIDIA GH200 GPUs on the JUPITER supercomputer. We train BEAST as a 700-million-parameter model with 96 random weight samples on 384 nodes on 40 years of data for nearly one million gradient updates. This model achieves predictive skill scores competitive with state-of-the-art probabilistic atmospheric AI models and numerical models, and can predict extreme events with exceptional skill, while generating large ensembles 3 to 4 times faster than the current-best AI model. Our contribution unlocks the potential of high-fidelity uncertainty quantification in atmospheric AI models, heralding a new era for AI-based models in climate and Earth system sciences.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.12815",
  "author_total": 15,
  "authors": [
    {
      "name": "Deifilia Kieckhefen"
    },
    {
      "name": "Juan Pedro Gutiérrez Hermosillo Muriedas"
    },
    {
      "name": "Lars Helge Heyen"
    },
    {
      "name": "Mathis Bode"
    },
    {
      "name": "Iida Hakulinen"
    },
    {
      "name": "Andreas Herten"
    },
    {
      "name": "Chelsea Maria John"
    },
    {
      "name": "Thorsten Kurth"
    },
    {
      "name": "Anni Moisala"
    },
    {
      "name": "Asena Karolin Özdemir"
    },
    {
      "name": "Kaleb Phipps"
    },
    {
      "name": "Oskar Taubert"
    },
    {
      "name": "Arvid Weyrauch"
    },
    {
      "name": "Markus Götz"
    },
    {
      "name": "Charlotte Debus"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fzxxjq3pyg8jh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.12815",
  "fulltext_url": null,
  "id": "fzxxjq3pyg8jh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.12815",
  "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.DC"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.PF"
    ],
    [
      "arxiv",
      "physics.ao-ph"
    ],
    [
      "openalex",
      "1902|Meteorological Phenomena and Simulations"
    ]
  ],
  "openalex": "W7212485227",
  "pdf_url": "https://arxiv.org/pdf/2609.12815",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-11",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fzxxjq3pyg8jh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:07Z",
      "native_id": "2609.12815",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.12815"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    }
  ],
  "title": "4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling",
  "title_text": "4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:07Z",
  "url": "https://research.draconitic.com/paper/fzxxjq3pyg8jh",
  "venue": "arXiv",
  "versions": []
}