PhD Studentship: Leveraging probabilistic AI for heat-related health risk mitigation and adaptation. UNRISK NERC Centre for Doctoral Training PhD studentship 2025/26 Entry.

Understanding Uncertainty to Reduce Climate Risks (UNRISK) is a Centre for Doctoral Training – Recruiting now!

UNRISK is a Centre for Doctoral Training with fully funded PhD research opportunities at the University of Leeds, University College London, and the University of Exeter collaborating with over 40 external partners. UNRISK will train students with the multidisciplinary knowledge and skills across climate science, data science and decision science to tackle the pressing challenge of reducing the risks associated with rapid climate change. UNRISK will fund 40 PhD students in cohorts of 12-15 per year over three years, providing them with a stipend, university fees and residential training for 3 years and 9 months. Find out more at https://unrisk-cdt.ac.uk/ and browse the projects at https://unrisk-cdt.ac.uk/projects/.

Project Information

With temperature records having been broken repeatedly in recent decades, heat-stress is posing a serious health risk (e.g. the fatalities in the 2007 London marathon). This project aims to quantify the spatially-and-temporally varying heat-risk in the UK and to understand how this is affected by climate change. The project will leverage probabilistic (Bayesian) AI methods for modelling weather and health data provided by the UK Met Office, plus access to operational weather forecasts and climate projections. The project is at the interface between AI, environmental science, meteorology and epidemiology. Skills such as machine learning, environmental and health data manipulation, risk mapping and decision making under uncertainty are expected to be gained by the student, who will have the chance to be hosted at the Met Office as a visiting scientist.

The first challenge is the question of how to best use machine learning methods for understanding the relationship between heat-stress and health outcomes. Heat-stress is a combination of unfavourable temperature, humidity and wind-speed over a generally unknown number of hours/days etc. Appropriate data modelling tools will need to be utilised to understand health-risk as a function of heat-stress, allowing for socio-economic factors of the population-at-risk, in addition to the inherent spatio-temporal variability.

Advert information