PhD Studentship: Advancing Seasonal Weather Risk Assessment Using Machine Learning

This 3.5 year PhD project is open to home and overseas applicants. The successful candidate will receive a tax free annual stipend (depending on circumstances) set at the UKRI rate (£19,237 of 2024/25). We expect this to increase each year. Tuition fees will also be paid.

The increasing frequency and severity of extreme weather events, exacerbated by climate change, pose substantial risks to food security and result in widespread loss and damage to property. Seasonal weather risks, such as prolonged droughts, intense rainfall, and heatwaves, threaten agricultural productivity, infrastructure, and livelihoods, highlighting the need for more accurate and actionable predictive tools. Traditional seasonal forecasting methods rely heavily on dynamical models that simulate the propagation of teleconnections, such as El Niño–Southern Oscillation (ENSO) and the North Atlantic Oscillation (NAO). While these models provide valuable insights, they are computationally intensive and often operate at coarse spatial resolutions, limiting their effectiveness for localised risk assessment and decision-making.

This PhD project will leverage recent advances in machine learning to address these challenges by developing probabilistic graph neural network-based methods for seasonal weather risks at high temporal and spatial resolution. By adopting a hybrid approach that combines machine learning with causal inference methods, the project will identify key drivers of forecasting skill and uncover the influence of large-scale climate patterns on seasonal predictability. These advancements will support the proactive development of downstream climate risk management tools, focusing on optimising parametric insurance product structures.

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.

Please contact the supervisor for this project, Dr Rendani Mbuvha - rendani.mbuvha@manchester.ac.uk, before you apply. Please include details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project.

Advert information