{
  "abstract": "Effective climate risk assessment is hindered by the resolution gap between coarse global climate models and the fine-scale information needed for regional decision making. Existing downscaling methods struggle to bridge this gap: physics-based methods are too computationally expensive for large ensemble sampling of extreme events, while traditional statistical methods fail to capture multivariate spatiotemporal dependencies crucial to compound risk estimation. Furthermore, current machine learning approaches rely on temporally aligned training pairs, which are unavailable for free-running climate projections. Here we introduce GenFocal, an AI framework that generates statistically accurate, fine-scale weather from coarse climate projections without requiring paired simulated and observed events during training. GenFocal synthesizes complex and long-lived hazards, such as heatwaves and tropical cyclones, even when they are not well represented in the coarse climate projections. It also samples high-impact, rare events more accurately than leading methods. By translating large-scale climate projections into actionable localized information, GenFocal provides a powerful paradigm to improve climate adaptation and resilience strategies.",
  "abstract_shown": true,
  "affiliations": [
    "Google Research, Mountain View, CA, USA",
    "California Institute of Technology, Pasadena, CA, USA",
    "Now at General Motors Sunnyvale Tech Center, Sunnyvale, CA, USA",
    "Now at Meta, Menlo Park, CA, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Zhong Yi Wan",
      "orcid": "0000-0001-7264-3628"
    },
    {
      "affs": [
        0
      ],
      "name": "Ignacio Lopez‐Gomez",
      "orcid": "0000-0002-7255-5895"
    },
    {
      "affs": [
        0
      ],
      "name": "Robert W. Carver",
      "orcid": "0000-0001-5085-0773"
    },
    {
      "affs": [
        1,
        0
      ],
      "name": "Tapio Schneider",
      "orcid": "0000-0001-5687-2287"
    },
    {
      "affs": [
        0,
        2
      ],
      "name": "John Anderson"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Fei Sha",
      "orcid": "0009-0006-1733-5482"
    },
    {
      "affs": [
        0
      ],
      "name": "Leonardo Zepeda-Núñez",
      "orcid": "0000-0002-7310-6493"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e5ebfqwrqhjhg.bib",
  "cited_by": 20,
  "doi": "10.1038/s42256-026-01308-7",
  "fulltext_url": null,
  "id": "e5ebfqwrqhjhg",
  "issns": [
    "2522-5839"
  ],
  "landing_url": "https://doi.org/10.1038/s42256-026-01308-7",
  "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",
      "2306|Climate variability and models"
    ]
  ],
  "openalex": "W4405301131",
  "pdf_url": "https://www.nature.com/articles/s42256-026-01308-7.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/e5ebfqwrqhjhg.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:17Z",
      "native_id": "W4405301131",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s42256-026-01308-7"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2306|Climate variability and models",
      "subfield": "climate"
    }
  ],
  "title": "Regional climate risk assessment from climate models using probabilistic machine learning",
  "title_text": "Regional climate risk assessment from climate models using probabilistic machine learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:20Z",
  "url": "https://research.draconitic.com/paper/e5ebfqwrqhjhg",
  "venue": "Nature Machine Intelligence",
  "versions": []
}