{
  "abstract": "Species distribution models (SDMs) are central to biodiversity forecasting and conservation decision-making. As ecological datasets grow in size, dimensionality, and resolution, there is a need for flexible yet scalable SDMs tailored to large-scale species observation data. Inspired by the masked modeling approach in natural language processing and genomics, if we treat each species' presence or absence as a token, and a site's species assemblage together with its spatio-temporal and ecological covariates as analogous to a sentence, we can learn joint co-occurrence structure by reconstructing masked species from their neighboring sites. We propose STEM-LM, a Transformer-based SDM that applies masked language modeling to multi-species distribution modeling with explicit consideration of spatio-temporal structure. By applying dynamic masking rates during training, a single trained model can support both purely spatio-temporal/ecological prediction and prediction conditioned on arbitrary subsets of observed species. On a North American butterfly dataset, a Northeast US demersal fish trawl survey, and a global plant distribution dataset, STEM-LM has the highest discrimination (AUROC) among all compared methods, and its rank-monotonicity (continuous Boyce index) is either the best or close to the best.",
  "abstract_shown": true,
  "affiliations": [
    "University of California, Berkeley"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "J. K. Li"
    },
    {
      "name": "W. Lim"
    },
    {
      "name": "R. Rheem"
    },
    {
      "name": "F. Callahan"
    },
    {
      "name": "L. Y. Raskin"
    },
    {
      "name": "M. Lemmon-Kishi"
    },
    {
      "affs": [
        0
      ],
      "name": "R. Nielsen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cry38j231k90j.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.05.13.724718",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.05.13.724718v2.full",
  "id": "cry38j231k90j",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.05.13.724718v2",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "ecology"
    ],
    [
      "openalex",
      "2302|Species Distribution and Climate Change"
    ]
  ],
  "openalex": "W7161237218",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.05.13.724718v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cry38j231k90j.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:09Z",
      "native_id": "10.64898/2026.05.13.724718",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.05.13.724718v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:ecology",
      "subfield": "ecology"
    }
  ],
  "title": "STEM-LM: Spatio-Temporal Ecological Modeling via Masked Language Model for Multi-Species Distribution",
  "title_text": "STEM-LM: Spatio-Temporal Ecological Modeling via Masked Language Model for Multi-Species Distribution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:09Z",
  "url": "https://research.draconitic.com/paper/cry38j231k90j",
  "venue": "bioRxiv",
  "versions": []
}