EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An emerging tool for ecological surveillance: machine learning to identify small mammals from their footprints

Zoe C. Jewell, Debbie Liske, Nico Avenant, Maria Oosthuizen, Lynn Carlson, Duncan MacFadyen, Sky Alibhai

Frontiers in Ecology and Evolution · 19.11.2026 · 14

DOI: 10.3389/fevo.2026.1983895 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Ecology and Evolution, online erschienen am 19.11.2026. Verfasst von Zoe C. Jewell und 6 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JRS Biodiversity Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small mammals are important ecological indicators but remain under-represented in biodiversity monitoring because traditional survey methods can be labor-intensive, invasive, or difficult to scale. We introduce a non-invasive ecological surveillance approach that combines trackplates and computer vision to identify species from individual footprint images. By converting footprints into a standardized digital data stream, the method addresses a critical gap in biodiversity monitoring and ecological surveillance. Between October 2023 and March 2025, footprints from identified small mammal species were collected at five sites in South Africa. These data were curated into a reference library and processed into a benchmark dataset comprising 3,355 cropped footprint images from 122 usable trackplates representing 11 species. Each footprint received a primary species label and an auxiliary front-versus-hind label within a multi-task learning framework designed to promote anatomically meaningful feature learning. The final DINOv3-based Vision Transformer was evaluated using five-fold cross-validation grouped at the trackplate level to ensure assessment on previously unseen trackplates and prevent information leakage. The model achieved a mean cross-validation accuracy of 89.2% (SD = 2.4%) across five folds and a best-fold accuracy of 92.5%. Balanced species-level performance was also strong, with a mean macro F1 score of 88.7% (SD = 3.0%). Several species were classified with near-perfect performance despite substantial variation in footprint orientation, completeness, and source-image quality. Residual errors were concentrated among a small subset of morphologically similar species. Explainable AI analyses indicated that the model organized footprints according to morphological similarity and relied on biologically meaningful features, including toe placement, pad geometry, and overall footprint shape, rather than plate-specific artifacts. These findings demonstrate that individual small mammal footprints contain sufficient morphological information for robust species-level discrimination. This approach enables small mammal species-richness data to serve as a scalable, standardized, and non-invasive indicator, with strong potential to extend small mammal monitoring across protected areas, production landscapes, and community-based schemes aligned with the Kunming–Montreal Global Biodiversity Framework.

Förderung

  • JRS Biodiversity Foundation

Zitieren

APA

Jewell, Z. C., Liske, D., Avenant, N., Oosthuizen, M., Carlson, L., MacFadyen, D., & Alibhai, S. (2026). An emerging tool for ecological surveillance: machine learning to identify small mammals from their footprints. Frontiers in Ecology and Evolution, 14. https://doi.org/10.3389/fevo.2026.1983895

Vancouver

Jewell ZC, Liske D, Avenant N, Oosthuizen M, Carlson L, MacFadyen D, et al. An emerging tool for ecological surveillance: machine learning to identify small mammals from their footprints. Frontiers in Ecology and Evolution. 2026;14. doi:10.3389/fevo.2026.1983895

BibTeX
@article{Jewell2026,
  author = {Jewell, Zoe C. and Liske, Debbie and Avenant, Nico and Oosthuizen, Maria and Carlson, Lynn and MacFadyen, Duncan and Alibhai, Sky},
  title = {An emerging tool for ecological surveillance: machine learning to identify small mammals from their footprints},
  journal = {Frontiers in Ecology and Evolution},
  year = {2026},
  volume = {14},
  doi = {10.3389/fevo.2026.1983895}
}
Kostenlos starten →