Supervisor

Suitable for

Abstract

Traditionally, disease mapping has heavily leaned on statistical models such as multivariate normal distributions and Gaussian Processes. However, the ever-evolving landscape of machine learning, especially in the realm of neural networks, presents an untapped potential for disease mapping. This project aims to harness the latest advancements in spatial data modelling and bring them to the forefront of disease mapping. The goal of the project is to explore cutting-edge techniques, including Bayesian inference with Markov Chain Monte Carlo (MCMC), to unlock new insights and capabilities in disease mapping, bridging the gap between traditional statistical methods and the power of deep learning.