Back to home

Join my group

Open positions

I'm recruiting students to work on AI and optimisation for biodiversity conservation.

Combinatorial Optimisation for Constrained Dynamic Conservation Planning

Funding
Funded
Deadline
Level
PhD Scholarship
Institution
Monash University

We are excited to offer a 3.5-year, fully funded PhD scholarship in Data Science and Artificial Intelligence at Monash University. This project focuses on combinatorial optimisation for conservation planning, and will develop new methods to account for practical constraints and stakeholder requirements in biodiversity conservation, including how plans should adapt as conditions change over time.

This is an exciting opportunity to work with experts in combinatorial optimisation and decision science, and directly with conservation agencies to deliver impactful outcomes for nature and biodiversity. The PhD candidate will develop cutting-edge skills in data science and AI that may include mixed-integer linear and non-linear programming, constraint programming, stochastic optimisation and reinforcement learning. The candidate will join a cohort of researchers at Monash’s Environmental Informatics Hub, whose mission is to develop AI to help reverse biodiversity loss.

The scholarship is open to domestic and international applicants. Applicants can be from a quantitative discipline (mathematics, computer science, data science, economics, AI) or from ecology and biology with a willingness to learn mathematical optimisation.

Expressions of interest close 20 November 2026, for an early 2027 start. However, we encourage candidates to apply as early as possible. To apply, complete the EOI form and provide a one-page CV and academic transcripts.

Suggested reading

Combinatorial Optimisation Mixed-Integer Programming Constraint Programming Stochastic Optimisation Reinforcement Learning Conservation Planning

Decision AI for Biodiversity Conservation

Funding
Funded
Deadline
Open until filled
Level
PhD Scholarship
Institution
Monash University

Supervised by Prof. Iadine Chades, Dr Lily Xu (Columbia University) & Dr Frankie Cho

Conservation decisions must balance learning (surveying, monitoring, reducing uncertainty) and acting (managing threats, reducing extinction risk) — yet existing approaches too often optimise one at the expense of the other. This PhD will develop Decision AI methods that explicitly integrate information-gathering and management objectives, enabling decision-makers to learn about complex ecological systems while delivering effective conservation outcomes.

The project sits at the intersection of: decision-making under uncertainty; sequential and adaptive decision processes; multi-objective optimisation; Markov Decision Processes; reinforcement learning; value of information; and biodiversity conservation. The successful candidate will join the Environmental Informatics Hub.

Decision AI Reinforcement Learning MDPs Value of Information Conservation

Mapping Monitoring Gaps: Aligning Species Data with Biodiversity Observation Effort in Australia

Funding
Self-funded
Deadline
Open until filled
Level
PhD / Honours
Institution
University of Newcastle

Supervised by Dr Brooke Williams (UoN) & Dr Frankie Cho (Monash)

Observation efforts often fail to align with expert knowledge of species distributions. This project will compare expert-derived species range maps with existing monitoring data to identify spatial gaps and mismatches in survey effort, highlighting priority regions where targeted, low-cost monitoring could rapidly improve biodiversity knowledge and inform conservation decision-making.

Spatial Planning GIS Species Monitoring Biodiversity Data

Funding is not attached — interested applicants should reach out to Dr Brooke Williams to discuss ideas and potential funding.

Students

Current student projects

Positions filled

These positions are filled, but students are welcome to suggest new ideas that build on these projects. Get in touch to discuss your idea and explore funding opportunities.

5 students currently in the group

Back to home