Learning and Decision-Making Under Uncertainty in Public Health

Decision-making under uncertainty is a fundamental challenge in AI and data science, particularly in dynamic settings where observations are collected sequentially and decisions influence future outcomes. This project will develop novel machine learning and statistical methods for adaptive learning, sequential decision-making, and control, motivated by applications in public health and epidemiology.

The project will focus on methodological advances in reinforcement learning (RL), active learning, Bayesian decision theory, and stochastic optimisation for partially observed and evolving systems. Key research directions include: (1) adaptive data acquisition strategies that maximise information gain under resource constraints; (2) RL-based approaches for sequential intervention and control; and (3) robust learning methods that adapt to incomplete observations, changing environments, and distributional shifts.

The research will combine probabilistic modelling, network-based representations, and modern AI methods to enable scalable and interpretable decision-making in complex systems. Applications will include adaptive disease surveillance, outbreak monitoring, resource allocation, and intervention planning using dynamic mobility and contact networks as motivating examples. The methodological contributions have broader relevance to sequential optimisation and decision-making problems across AI and data science.

The ideal candidate will have foundational knowledge of machine learning and strong self-motivation. You will be supervised by Dr. Mengyan Zhang (https://mengyanz.github.io/), whose research focuses on sequential decision making and public health. Dr. Zhang has published in leading venues including Nature, PNAS, ICML, AAAI, etc. She collaborates widely through the Machine Learning and Global Health network, including with researchers at the University of Oxford, Imperial College London, and the National University of Singapore.

Funding Notes

4 year University Scholarship to start 27/28 academic year - Minimum tax-free stipend at the current UKRI rate (for 2025/26 standard stipend is £20,780, RTSG £8,400, full Tuition Fee covered).