DeepFaune New England: A species classification model for trail camera images in northeastern North America
November 14, 2025
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.
Citation Information
| Publication Year | 2025 |
|---|---|
| Title | DeepFaune New England: A species classification model for trail camera images in northeastern North America |
| DOI | 10.1002/ece3.72174 |
| Authors | Laurence A. Clarfeld, Katherine D. Gieder, Angela K. Fuller, Zhongqi Miao, Alexej P.K. Sirén, Shevenell M. Webb, Toni Lyn Morelli, Jillian R. Kilborn, Catherine B. Callahan, Leighlan S. Prout, Rachel Cliché, Riley K. Patry, Christopher Bernier, Susan Staats, Therese M. Donovan |
| Publication Type | Article |
| Publication Subtype | Journal Article |
| Series Title | Ecology and Evolution |
| Index ID | 70273069 |
| Record Source | USGS Publications Warehouse |
| USGS Organization | Coop Res Unit Leetown |
Related
Toni Lyn Morelli, Ph.D.
Research Ecologist, Northeast CASC
Research Ecologist, Northeast CASC
Email
Phone
Related
Toni Lyn Morelli, Ph.D.
Research Ecologist, Northeast CASC
Research Ecologist, Northeast CASC
Email
Phone