{
  "abstract": "Traditional wildfire models rely on rigid, low-dimensional parameters and static fuel maps, frequently underpredicting fire spread. To address this weakness, we introduce a hybrid deep-learning parameterized Probabilistic Cellular Automata (CA) framework implemented in JAX. Our approach employs a Multi-Scale Convolutional Neural Network to dynamically generate spatially varying parameters that govern fire-spread probability, wind alignment, and slope influence. This hybrid design captures complex, nonlinear environmental interactions while preserving the physical interpretability of the underlying three-state CA. The JAX implementation enables hardware acceleration and gradient-based parameter calibration. Evaluated on six large-scale wildfires in the western United States, the model maintains IoU > 0.6 over 72-hour forecast horizons after a 10-day data assimilation window during which the model is fitted incrementally to observed perimeters; the resulting forecast is a conditional projection of fire growth under the suppression regime already ncoded in those observations.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Ecological Informatics, Volume 97, 2026, 103928",
  "arxiv": "2606.11676",
  "author_total": 5,
  "authors": [
    {
      "name": "Maksym Zhenirovskyy"
    },
    {
      "name": "Ion Matei"
    },
    {
      "name": "Rohit Vuppala"
    },
    {
      "name": "Takuya Kurihana"
    },
    {
      "name": "Hon Yung Wonga"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/020zmt86p206y.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.11676",
  "fulltext_url": null,
  "id": "020zmt86p206y",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.11676",
  "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.CE"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2606.11676",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-10",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/020zmt86p206y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:06Z",
      "native_id": "2606.11676",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.11676"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Neural-Parameterized Cellular Automata for Wildfire Spread",
  "title_text": "Neural-Parameterized Cellular Automata for Wildfire Spread",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:06Z",
  "url": "https://research.draconitic.com/paper/020zmt86p206y",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1016/j.ecoinf.2026.103928",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}