Online Talk: Footprints for the Future talk by Jazz Woollard

Monitoring small mammal populations gives us insight into the natural world by providing us information such as response to disturbance, success of management strategy, and overall habitat health and ecosystem function.

Traditionally, small mammal data has been collected using live trapping in the field, often using capture-mark-recapture (CMR) methods. Although widely used, little is known about the behavioural, physiological, psychological, and ecological impacts that trapping has on individuals and the ecosystems they are a part of. Therefore, it is important to explore non-invasive methods of data collection where possible and practicable. 

WildTrack, a US-based organisation, has been developing deep learning models to support non-invasive monitoring of terrestrial mammals. This approach uses Footprint Identification Technology (FIT) to identify species from their footprints.

This project, based at Wildwood Trust, in collaboration with The Mammal Society, Peoples Trust for Endangered Species and Kent Mammal Group works in collaboration with WildTrack to develop this technology and apply it to UK small mammals, opening it up to citizen science. 

While developing non-invasive survey techniques is essential, it is equally important to consider the welfare of animals involved in reference data collection. 

Therefore big focus during early stages of this project was to design a footprint collection method that minimises behavioural disturbance and welfare impacts. This has involved creating and refining a footprint collection box that reduces stress while capturing high-quality prints.

This talk will outline the purpose of the project, methodology and challenges of applying FIT to small mammals, emphasise the importance of animal welfare and behaviour in data collection, and demonstrate how deep learning models compliment conventional wildlife monitoring.

Join the Zoom Meeting on Oct 30, 2026 at 07:30 PM:

https://us02web.zoom.us/j/83787546490?pwd=6VllbJHY3RqfY7VQ2yBkUIdv1S5fos.1

Meeting ID: 837 8754 6490
Passcode: 650209