"PhD Studentship: Evolving Surrogate Models: Machine Learning & Evolutionary Computation for Emulation in Climate Models, NERC GW4+ DTP PhD studentship for September 2026 Entry"

About the Partnership

This project is one of a number that are in competition for funding from the NERC Great Western Four+ Doctoral Training Partnership (GW4+ DTP). The GW4+ DTP consists of the Great Western Four alliance of the University of Bath, University of Bristol, Cardiff University and the University of Exeter plus five Research Organisation partners: British Antarctic Survey, British Geological Survey, Centre for Ecology and Hydrology, the Natural History Museum and Plymouth Marine Laboratory. The partnership aims to provide a broad training in earth and environmental sciences, designed to train tomorrow’s leaders in earth and environmental science. For further details about the programme please see http://nercgw4plus.ac.uk/

For eligible successful applicants, the studentships comprises:

• An stipend for 3.5 years (currently £20,780 p.a. for 2026/27) in line with UK Research and Innovation rates
• Payment of university tuition fees
• The budget for project costs is £9,000 which can be used for computer, lab, and fieldwork costs necessary for you to conduct your research.
• There is also a conference budget of £2,000 and individual Training Budget of £1,000 for specialist training

Project aims and methods:

The Met Office aims to help its customers stay safe and thrive by producing reliable weather and climate information. Numerical models of the climate system are an important tool to help achieve this goal. However, the computational expense of these models limits their use for generating forecasts, constraining the spatial resolution, level of physical complexity, and number of ensemble members that can be run. Emulating expensive processes could allow more data to be generated from better models, at lower cost.

The central science question is: how can machine learning and evolutionary computation be used to emulate expensive climate model processes, such as sea-ice rheology and vertical mixing in the ocean, to deliver forecasts at lower computational cost? This project will develop surrogate models optimised with evolutionary algorithms to address combinatorial optimisation in model design and the noisy nature of climate data.

The Doctoral Researcher will receive on-the-job training in machine learning and evolutionary optimisation at the University of Exeter, and in climate model evaluation and configuration at the Met Office. This strong multidisciplinary partnership will potentially reduce computational costs, lowering the carbon footprint of climate science in the long-term within NERC’s Climate Change and Risk theme.

CASE Partner

The Met Office are providing support and guidance in accessing and interpreting training data and domain expertise on sea-ice and ocean modelling.