{
  "abstract": "Machine learning models have shown great success in predicting weather up to two weeks ahead, outperforming process-based benchmarks 1 , 2 , 3 , 4 , 5 . However, most existing approaches do not fully integrate data assimilation into the prediction workflow 6 , 7 , and often suffer from error accumulation in autoregressive computation, limiting their applicability to predictions beyond the medium range 8 and climate projections 9 . We introduce Generative Assimilation and Prediction (GAP), a unified deep generative framework that connects data assimilation, weather forecasting, and climate simulation through a shared probabilistic representation of atmospheric states. GAP learns the climatological distribution from reanalysis data, and adapts it to different tasks by incorporating observational, predictive, and forcing constraints. Evaluated across a range of weather-climate tasks, GAP produces probabilistic weather forecasts competitive with leading forecasting systems, using its own assimilated initial states derived from 5% synthetic perfect observations, with particular skill in capturing extreme events such as atmospheric rivers, heatwaves and the Madden-Julian Oscillation. At seasonal timescales, GAP shows promising predictive skill when constrained by oceanic boundary forcing. Moreover, GAP supports stable millennial-scale climate simulations that reproduce atmospheric variability from daily weather fluctuations to decadal oscillations. These results suggest that generative modeling of the climatological distribution offers a viable foundation for seamless weather and climate prediction, thereby opening a path toward integrated, observation-to-climate workflows.",
  "abstract_shown": true,
  "affiliations": [
    "Complexity Science, Potsdam Institute for Climate Impact Research, Potsdam, Germany",
    "Earth System Modelling, School of Engineering and Design, Technical University of Munich, Munich, Germany",
    "Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China",
    "School of Atmospheric Sciences and Key Laboratory of Mesoscale Severe Weather/Ministry of Education, Nanjing University, Nanjing, China",
    "Chinese Academy of Meteorological Sciences, Beijing, China",
    "College of Meteorology and Oceanography, National University of Defense Technology, Changsha, China",
    "Academy of Advanced Interdisciplinary Studies, Wuhan University, Wuhan, China",
    "Hubei Center for Applied Mathematics, Wuhan University, Wuhan, China",
    "School of Atmospheric Sciences, Sun Yat-Sen University, Zhuhai, China",
    "Department of Atmospheric and Oceanic Sciences, School of Physics, Peking University, Beijing, China",
    "Institute of Ocean Research, School of Physics, Peking University, Beijing, China",
    "Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing, China",
    "China Meteorological Administration Key Laboratory for Climate Prediction Studies, National Climate Center, Beijing, China",
    "Xiong’an Institute of Meteorological Artificial Intelligence, Xiong’an, China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 16,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Shangshang Yang",
      "orcid": "0009-0006-3662-5813"
    },
    {
      "affs": [
        2
      ],
      "name": "Congyi Nai",
      "orcid": "0009-0006-2037-6162"
    },
    {
      "affs": [
        4,
        2
      ],
      "name": "Xinyan Liu",
      "orcid": "0000-0003-3078-3563"
    },
    {
      "affs": [
        2
      ],
      "name": "Weidong Li"
    },
    {
      "affs": [
        2
      ],
      "name": "Jie Chao",
      "orcid": "0000-0002-9153-3552"
    },
    {
      "affs": [
        5,
        2
      ],
      "name": "Jingnan Wang",
      "orcid": "0000-0002-3165-6876"
    },
    {
      "affs": [
        6,
        7
      ],
      "name": "Leyi Wang",
      "orcid": "0000-0001-5813-9505"
    },
    {
      "affs": [
        8
      ],
      "name": "Xichen Li",
      "orcid": "0000-0001-6325-6626"
    },
    {
      "affs": [
        9,
        10,
        11
      ],
      "name": "Xichen Li"
    },
    {
      "affs": [
        2
      ],
      "name": "Xi Chen",
      "orcid": "0000-0002-9952-9048"
    },
    {
      "affs": [
        12,
        13
      ],
      "name": "Bo Lu"
    },
    {
      "affs": [
        9,
        10,
        11
      ],
      "name": "Xin Li"
    },
    {
      "affs": [
        2
      ],
      "name": "Ziniu Xiao",
      "orcid": "0000-0003-0509-5267"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Niklas Boers",
      "orcid": "0000-0002-1239-9034"
    },
    {
      "affs": [
        3
      ],
      "name": "Huiling Yuan",
      "orcid": "0000-0003-4725-9039"
    },
    {
      "affs": [
        2
      ],
      "name": "Baoxiang Pan",
      "orcid": "0000-0002-3409-5568"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2q2q303w88qa6.bib",
  "cited_by": 27,
  "doi": "10.1038/s41612-026-01585-4",
  "fulltext_url": null,
  "id": "2q2q303w88qa6",
  "issns": [
    "2397-3722"
  ],
  "landing_url": "https://doi.org/10.1038/s41612-026-01585-4",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1902|Meteorological Phenomena and Simulations"
    ]
  ],
  "openalex": "W4416083465",
  "pdf_url": "https://www.nature.com/articles/s41612-026-01585-4.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/2q2q303w88qa6.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:15Z",
      "native_id": "W4416083465",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41612-026-01585-4"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:1902|Meteorological Phenomena and Simulations",
      "subfield": "atmospheric"
    }
  ],
  "title": "Generative assimilation and prediction for weather and climate",
  "title_text": "Generative assimilation and prediction for weather and climate",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:53Z",
  "url": "https://research.draconitic.com/paper/2q2q303w88qa6",
  "venue": "npj Climate and Atmospheric Science",
  "versions": []
}