DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America

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.

Authors

Institutions

Publication Details

Journal
Ecology and Evolution
Published
2025-11-01
DOI
https://doi.org/10.1002/ece3.72174
Citations
1
Primary Topic
Wildlife Ecology and Conservation
Type
article
Field-Weighted Citation Impact
1.72

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America

Therese M. Donovan, Rachel M. Cliché, Alexej P. K. Sirén, Toni Lyn Morelli et al.
1 citations
Ecology and Evolution
Wildlife Ecology and Conservation
1.72
article

DeepFaune New England: A Species Classification Model for Trail Camera Images in Northeastern North America

Therese M. Donovan, Rachel M. Cliché, Alexej P. K. Sirén, Toni Lyn Morelli, Susan Staats, Katherina Gieder, Catherine Callahan, Laurence A. Clarfeld, Tammy L. Wilson, Shevenell M. Webb, Angela K. Fuller, Christopher Bernier, Zhongqi Miao, Leighlan S. Prout, Jillian R. Kilborn, Scott Wixsom, Riley K. Patry
article en
1 citations

Abstract

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.

Ecology and EvolutionVol. 15(11)
Dartmouth College (US), University of Vermont (US), Green Mountain College (US), United States Geological Survey (US), Microsoft (United States) (US), New Hampshire Fish and Game Department (US), US Forest Service (US), United States Fish and Wildlife Service (US), University of New Hampshire (US), Cornell University (US), University of Massachusetts Amherst (US), Green Mountain Radio Research (United States) (US), Northeast Climate Adaptation Science Center (US), Maine Department of Inland Fisheries and Wildlife (US), NHTI - Concord's Community College (US), Vermont Fish & Wildlife Department (US), Woodlands Hospital (GB), Climate Adaptation Science Centers (US)
U.S. Fish and Wildlife Service, U.S. Geological Survey, California Department of Fish and Wildlife
Openalex Percentile: Top 12%
Wildlife Ecology and Conservation
1.72
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.