Background

Climate change is affecting human health, but evidencing how and by how much, is a challenge. The effects are often indirect, driven by interacting factors like temperature and air quality, while health data are frequently patchy or incomplete. This PhD will use interpretable, probabilistic AI methods to quantify current and future climate impacts on health across the UK and Europe. Working with the Met Office and The Cyprus Institute, you’ll utilise statistics, AI, environmental science and epidemiology to test how modern data-modelling techniques can turn climate, health and population data into knowledge that directly informs climate adaptation and policy. You’ll build skills in data analysis and modelling, environmental/health data handling, risk mapping and decision-making under uncertainty—with the chance to be hosted at the Met Office as a visiting scientist.

PhD project

Challenge 1: Modelling compounding environmental effects
Health outcomes rarely stem from a single environmental factor. They emerge from complex interactions between multiple exposures—temperature, air quality, humidity—that compound over time (cumulative stress) and vary across space (complex terrain, urban vs. rural settings). A core challenge is identifying AI modelling approaches that can best capture these layered, interacting effects, rather than treating each exposure in isolation.

Challenge 2: Building interpretable and decision-relevant models
Powerful models are only useful if they can be trusted and acted upon. This means addressing four linked problems: 1) quantifying uncertainty in predictions, so outputs reflect real confidence levels rather than false precision; 2) ensuring the models estimate quantities that actually matter for decision-making, not just statistically convenient ones; 3) validating models rigorously against real-world outcomes; and 4) incorporating population, demographic and socioeconomic data in ways that support causal—not merely associative—conclusions about health impacts.

Throughout, the project will draw on expertise and data from the Met Office and The Cyprus Institute to ground these methodological challenges in real climate and health data.

Applicant Profile

Students with a strong background in statistics and/or machine learning who want to apply these skills to environmental epidemiology and more generally the interface between climate change and health

Other Information

https://experts.exeter.ac.uk/19235-theo-economou
https://experts.exeter.ac.uk/43970-christophe-sarran
https://www.cyi.ac.cy/index.php/care-c/about-the-center/care-c-center-overview.html
https://www.metoffice.gov.uk/research/climate/climate-impacts/health