{
  "abstract": "Reducing tropical deforestation effectively requires spatially explicit data on deforestation dynamics. While past deforestation is now detected and mapped with high accuracy, producing reliable future forecasts remains a challenge. We present a deep learning approach for high-resolution deforestation forecasting in the Brazilian Amazon. We train a spatio-temporal ConvLSTM model on past deforestation maps and other covariates. Our model achieves an F1 score of 0.47 when forecasting one year ahead, substantially improving over comparable prior work. For multi-year predictions, we obtain promising results within a 3-year horizon, while sensitivity to shifts in deforestation dynamics suggests limitations for longer-term forecasts. We generate forecasts for years 2016–2018 across the Brazilian Amazon, and make them available through an interactive Google Earth Engine application. Our results demonstrate the potential for high-resolution, short- and medium-term forecasting that can support conservation efforts and help protect tropical forests.",
  "abstract_shown": true,
  "affiliations": [
    "École Polytechnique Fédérale de Lausanne (EPFL)",
    "EPFL",
    "University of Zurich"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jan Pisl",
      "orcid": "0009-0003-6357-8651"
    },
    {
      "affs": [
        0
      ],
      "name": "Gencer Sumbul",
      "orcid": "0000-0003-3690-3052"
    },
    {
      "affs": [
        1
      ],
      "name": "Gaston Lenczner"
    },
    {
      "affs": [
        2
      ],
      "name": "Jan Dirk Wegner"
    },
    {
      "affs": [
        1
      ],
      "name": "Devis Tuia",
      "orcid": "0000-0003-0374-2459"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2gpbrjnwbk8vp.bib",
  "cited_by": 0,
  "doi": "10.1088/1748-9326/aebda8",
  "fulltext_url": null,
  "id": "2gpbrjnwbk8vp",
  "issns": [
    "1748-9326"
  ],
  "landing_url": "https://iopscience.iop.org/article/10.1088/1748-9326/aebda8",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://iopscience.iop.org/article/10.1088/1748-9326/aebda8/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": "IOP Publishing",
  "ris": "https://research.draconitic.com/paper/2gpbrjnwbk8vp.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:21:18Z",
      "native_id": "10.1088/1748-9326/aebda8",
      "source": "crossref",
      "url": "https://iopscience.iop.org/article/10.1088/1748-9326/aebda8"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "issn:1748-9326",
      "subfield": "environmental-science"
    }
  ],
  "title": "Towards high-resolution forecasting of tropical deforestation with deep learning",
  "title_text": "Towards high-resolution forecasting of tropical deforestation with deep learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T00:21:34Z",
  "url": "https://research.draconitic.com/paper/2gpbrjnwbk8vp",
  "venue": "Environmental Research Letters",
  "versions": []
}