{
  "abstract": "Conventional deep convection schemes remain a primary source of uncertainty in global climate models, yet replacing them with data-driven alternatives while maintaining physical consistency and numerical stability is an open challenge. We present a hybrid configuration of the Community Atmosphere Model version 6 (CAM6), in which a fully connected deep neural network replaces the Zhang-McFarlane deep convection scheme (ZM), while radiation, turbulence, and other cloud processes are left unchanged. The network is trained on output from a storm-resolving global model - the global System for Atmospheric Modeling (gSAM) - using a coarse-graining approach to derive subgrid-scale convective fluxes and tendencies. This data-driven parameterization is ported to CAM6 and found to run stably for more than a decade while conserving energy and moisture. It produces a broadly realistic climatology without retuning the remaining parameterizations. Relative to the default Zhang-McFarlane scheme, the neural network parameterization substantially improves some long-standing model deficiencies. In particular, the biases in light precipitation and extreme precipitation are markedly reduced, and the diurnal cycle of tropical land precipitation shifts from a spurious midday peak over many regions to the observed late-afternoon peak. These results support targeted ML-based convection schemes as a viable path toward reducing systematic model errors in next-generation climate models.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.20405",
  "author_total": 8,
  "authors": [
    {
      "name": "Xavier J. Levine"
    },
    {
      "name": "Griffin Mooers"
    },
    {
      "name": "Judith Berner"
    },
    {
      "name": "Jack W. Atkinson"
    },
    {
      "name": "Marat F. Khairoutdinov"
    },
    {
      "name": "Janni Yuval"
    },
    {
      "name": "Dominic Orchard"
    },
    {
      "name": "Paul A. O'Gorman"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/863a27hpf083w.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.20405",
  "fulltext_url": null,
  "id": "863a27hpf083w",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.20405",
  "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",
      "physics.ao-ph"
    ],
    [
      "openalex",
      "1902|Meteorological Phenomena and Simulations"
    ]
  ],
  "openalex": "W7222338359",
  "pdf_url": "https://arxiv.org/pdf/2610.20405",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/863a27hpf083w.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:04Z",
      "native_id": "2610.20405",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.20405"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    }
  ],
  "title": "Improved Precipitation Variability in the Community Atmosphere Model through Implementation of a Neural-Network Deep Convection Scheme",
  "title_text": "Improved Precipitation Variability in the Community Atmosphere Model through Implementation of a Neural-Network Deep Convection Scheme",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:04Z",
  "url": "https://research.draconitic.com/paper/863a27hpf083w",
  "venue": "arXiv",
  "versions": []
}