Project Level: Winter

Project Duration:

4 weeks – 20-36 hours per week. Applicant will be required on-site for the project.


Fisheries play an important socio-economic role in Australia, but managing fisheries is challenging. One reason is due to many complexities associated with fisheries population dynamics: the population growth is affected by various random factors, yet limited amount of data is available for estimating a good model. This project aims to use a powerful mathematical framework for decision making called Partially Observable
Markov Decision Processes (POMDPs) to learn both the fishery dynamics and a management policy. The successful applicant will develop a POMDP model for this problem and perform experiments to evaluate the model.

Expected Outcomes:

Develop a general understanding of fisheries and their management.

Gain knowledge on POMDPs and some state-of-the-art solvers, and develop skills for applying POMDPs in solving decision making problems.

Develop skills in research design, implementation, experimentation, and communication.

A report documenting the work done and the findings.

Suitable for:

Essential: knowledge on probability theory and programming skills.
Desirable: knowledge on statistical decision theory, optimisation (numerical/combinatorial), operations research, mathematical modelling.

Further Information:

Email Dr Nan Ye for any inquiry on the project.

Project members

Dr Nan Ye

Lecturer in Statistics&Data Science
School of Mathematics and Physics