DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America
Ecology and Evolution · 2025-11 · 15 (11)
DOI: 10.1002/ece3.72174 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ecology and Evolution, online erschienen am 14.11.2025. Verfasst von Laurence A Clarfeld und 16 weiteren Autor:innen. Beteiligte Einrichtung: Vermont Cooperative Fish and Wildlife Research Unit, 302 Aiken Center University of Vermont Burlington Vermont USA. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vermont Fish and Wildlife Department, U.S. Geological Survey.
Abstract (Originalsprache)
The DeepFaune New England model classifies wildlife species in trail camera images, identifying 24 taxa from northeastern North America with high (97%) accuracy. The model was adapted from the DeepFaune model for identifying European wildlife, demonstrating the practicality of transfer learning across continents. The majority of training data is openly licensed, and the model itself is open source, enabling easy integration into camera trapping workflows. The open source software is available at ( https://code.usgs.gov/vtcfwru/deepfaune‐new‐england ), and has been further integrated into the PyTorch‐Wildlife framework.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Vermont Cooperative Fish and Wildlife Research Unit, 302 Aiken Center University of Vermont Burlington Vermont USA.
- Vermont Department of Fish and Wildlife Rutland Vermont USA.
- U.S. Geological Survey, New York Cooperative Fish and Wildlife Research Unit, Department of Natural Resources and the Environment Cornell University Ithaca New York USA.
- AI for Good Research Lab Microsoft Seattle Washington USA.
- Earth Systems Research Center, Institute for the Study of Earth, Oceans, and Space University of New Hampshire Durham New Hampshire USA.
- Maine Department of Inland Fisheries and Wildlife Augusta Maine USA.
ORCID-Profile: Laurence A Clarfeld, Angela Fuller, Zhongqi Miao, Alexej P K Sirén, Toni Lynn Morelli, Tammy L Wilson, Scott Wixsom, Therese M Donovan
Förderung
- Vermont Fish and Wildlife Department
- U.S. Geological Survey
Zitieren
APA
Clarfeld, L. A., Gieder, K. D., Fuller, A., Miao, Z., Sirén, A. P. K., Webb, S. M., Morelli, T. L., Wilson, T. L., Kilborn, J., Callahan, C. B., Prout, L. S., Cliche, R., Patry, R. K., Bernier, C., Staats, S., Wixsom, S., & Donovan, T. M. (2025). DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America. Ecology and Evolution, 15(11). https://doi.org/10.1002/ece3.72174
Vancouver
Clarfeld LA, Gieder KD, Fuller A, Miao Z, Sirén APK, Webb SM, et al. DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America. Ecology and Evolution. 2025;15(11). doi:10.1002/ece3.72174
BibTeX
@article{Clarfeld2025,
author = {Clarfeld, Laurence A and Gieder, Katherina D and Fuller, Angela and Miao, Zhongqi and Sirén, Alexej P K and Webb, Shevenell M and Morelli, Toni Lynn and Wilson, Tammy L and Kilborn, Jillian and Callahan, Catherine B and Prout, Leighlan S and Cliche, Rachel and Patry, Riley K and Bernier, Christopher and Staats, Susan and Wixsom, Scott and Donovan, Therese M},
title = {DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America},
journal = {Ecology and Evolution},
year = {2025},
volume = {15},
number = {11},
doi = {10.1002/ece3.72174}
}
EUVIMED