Skip to main content

Decision AI for biodiversity

Primary supervisor

Iadine Chades

Adaptive sequential decisions to maximise information gain and biodiversity outcomes

This PhD research aims to develop and evaluate novel adaptive decision-making algorithms that guide conservation actions under uncertainty, with the dual goals of maximizing biodiversity outcomes and information gain. The project will integrate approaches from decision theory, Bayesian experimental design, Partially Observable Markov decision processes, reinforcement learning and ecological modelling to support sequential decision-making in dynamic environments. By simulating and applying these novel algorithms to real-world conservation case studies, the research will demonstrate how targeted information acquisition can improve the timing, location, and type of interventions. Ultimately, the work seeks to enhance the efficiency and impact of biodiversity conservation under limited resources and shifting ecological conditions.
 

Required knowledge

Relevant bibliography:

- Chades, I., Carwardine, J., Martin, T., Nicol, S., Sabbadin, R., & Buffet, O. (2012). MOMDPs: a solution for modelling adaptive management problems. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 26, No. 1, pp. 267-273).
- Blau, T., Bonilla, E. V., Chades, I., & Dezfouli, A. (2022, June). Optimizing sequential experimental design with deep reinforcement learning. In International conference on machine learning (pp. 2107-2128). PMLR.
- Péron, M., Becker, K., Bartlett, P., & Chades, I. (2017, February). Fast-tracking stationary MOMDPs for adaptive management problems. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 31, No. 1).
- Chadès, I., Pascal, L. V., Nicol, S., Fletcher, C. S., & Ferrer‐Mestres, J. (2021). A primer on partially observable Markov decision processes (POMDPs). Methods in Ecology and Evolution , 12 (11), 2058-2072.

Project funding

Other

Learn more about minimum entry requirements.