Scientific Papers

Our Publications

Animating the Dead | Christopher Evelyn, Constance Woodman, Seth Frazer, Connor Foley, Donald Brightsmith, and Katja Seltmann

 Location-specific machine learning models trained on synthetic images represent a scalable paradigm for quantifying biodiversity. Digital images of specimens or samples can be manipulated and combined with computer-generated scene elements to produce nearly infinite synthetic images for training machine learning models. Application of this method for the automatic cataloging of wildlife from camera trap images is of urgent need during this time of high extinction rate and environmental change.

Github Repository 

Dataset : Creating Site Specific Synthetic ML Training Datasets for Conservation: Sample Synthetic Training Dataset

NVSS hatching prediction poster

Ridlon, Ashley Predicting hatching dates for avian species using infrared cameras and machine learning models

Events and Conferences

Creating and Using Synthetic Data Sets to Train Machine Learning Models For Species Level Identification of Herpetofauna In-Situ

Ecological Society of America Conference, Montreal, Canada


Seth Frazer, Christopher J. Evelyn, Constance J. Woodman

American Ornithological Society & Birds Carribean Ornithological conference

San Juan, Puerto Rico


Woodman, C. J. 2022, June 27 – 2 July. USDA open-source technology: Smart camera traps for nests [Conference presentation]. American Ornithological Society & Birds Carribean 2022 Ornithological Conference, San Juan, Puerto Rico.

National Veterinary Scholars Symposium 2022

University of Minnesota


Woodman, C. J.