Decision AI for biodiversity

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.