Modelling Species’ Movements and Interactions Using Camera Traps and AI

This project is available from the academic year 2025/26 onwards.

Theme: Environmental Physics & Mathematical Modelling

Primary Supervisor:

Allan Tucker

Institute of Environment, Health and Societies, Brunel

Allan Tucker's Profile Picture

Secondary Supervisor:

Chris Carbone

Biodiversity and Macroecology Theme, IOZ

Chris Carbone's Profile Picture

Project Description:

Camera traps are a vital tool for ecologists to enable them to monitor wildlife over large areas in order to determine population changes, habitat, and behaviour. As a result, camera-trap datasets are rapidly growing in size. Recent advancements in Artificial Neural Networks (ANN) have emerged in image recognition and detection tasks which are now being applied to automate camera-trap labelling. This means that there are a growing number of pre-labelled datasets (from both human and AI methods). This project will explore how we can use these labelled images (along with their time and location tags) in conjunction with spatio-temporal models and in particular probabilistic graphical models to further improve automated classification of the images and reason about animal behaviour. Spatial Bayesian networks can be used to model these datasets and explore species behaviours (how they move and distribute themselves) and interactions (how they distribute in relation to other species).

Evans, BC., Tucker, A., Wearn, OR. and Carbone, C. (2021) ”.Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Ghent, Belgium. 2 – 18 September. Springer International Publishing. pp. 26 – 37. ISSN: 1865-0929

Trifonova, N., Kenny, A., Maxwell, D., Duplisea, D., Fernandes, J. and Tucker, A. (2015) ‘Spatio-temporal Bayesian network models with latent variables for revealing trophic dynamics and functional networks in fisheries ecology’. Ecological Informatics, 30. pp. 142 – 158. ISSN: 1574-9541

Policy Impact of Research:

Camera-traps are becoming one of the main techniques to monitor mammal communities across the globe, however, the use of these data have largely been limited to gain understanding of population distributions. This project will be used to enhance our understanding of animal behaviour, species interactions and ecosystem function which will have broader implications to human impacts on the environment.

Stay informed

Click here to subscribe to our RSS newsletter by email.

Find Us

University College London is the administrative lead.

North-West Wing, UCL, Gower Street, London, WC1E 6BT

Follow us on Twitter