ML-driven Design for Fusion Reactors

The UKRI AI Centre for Doctoral Training (CDT) in Decision Making for Complex Systems is a joint CDT between The University of Manchester and the University of Cambridge. The CDT provides funding for four years of advanced studies towards a PhD. The first year consists of a taught program at Manchester that will cover the fundamentals of Machine Learning. This year is followed by three years of research at either at Manchester or Cambridge. Please note the research element of the PhD will take place at the host institution of the supervisor listed for each project.

The goal of a fusion reactor is to confine plasma at a sufficiently high temperature to generate fusion reactions, allowing the generation of electricity. A leading candidate for building a practically useful fusion reactor — one that produces more energy that is required to begin the reaction — is a confinement system laid out in a toroidal structure known as a tokamak. However, in order to ensure efficiency of the tokamak, a wide variety of physics and engineering challenges must be resolved within the limited amount of space available in the reactor, thus posing a complicated design problem. Moreover, evaluating the suitability of any candidate reactor is a laboriously slow process, involving multiple levels of computationally expensive simulations and requirements from multiple stakeholders. Consequently, traditional design processes are unsuitable, as they require many design iterations and explore only a small fraction of possible design possibilities.

To demonstrate the complexity of designing a fusion reactor system, we can look at just one of its many key components — the toroidal field (TF) coils. The TF are responsible for the generation of the magnetic pressure confining the plasma and thus must be carefully optimised to minimise the toroidal field variations (ripple) occurring at the plasma boundaries that drive the overall performance of the tokamak. However, as choices in the TF influences various other practical aspects of the tokamak design, from the distribution of the electromechanical forces (structural integrity) to the size of the reactor (financial cost), the TF cannot be designed in isolation, without a system-level understanding of the vast overall reactor design space.

In this project, we will work with scientists from the UK Atomic Energy Authority (UKAEA) to develop novel ML-driven optimisation routines that help tackle the intricate design challenges inherent in developing sustainable fusion energy solutions. In particular, we will depart from traditional reactor design processes, and instead follow the paradigm of Bayesian sequential design, which has risen as an effective ML-driven strategy for high-cost design problems over complex search spaces through methods such as Bayesian Optimisation (BO) and active learning. Indeed, the potential benefits of such AI-based exploration for optimum fusion reactor components has already been demonstrated in initial work by scientists at UKAEA, where existing BO methodology was able to successfully design a simplified 8-dimensional parametrisation of the TF coils. However, extending this proof-of-concept work to a level where it can accelerate progress in nuclear fusion research requires novel methodology in key areas such as 1) high-dimensional and multi-fidelity optimization, leveraging different levels of computational simulations; 2) optimisation of manifolds to allow direct optimisation of 3D structures like TF coils; and 3) ML-guided human interaction, devising methods for effective collaboration between ML algorithms and expert scientists even when objectives are poorly defined or not fully know before beginning optimisation.

This project is co-funded by UKAEA.

Entry requirements

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.

How to Apply

As the CDT has only recently been awarded we strongly encourage you to contact the supervisor of the project you are interested in with your CV and supporting documents. You will have a chance to meet with prospective supervisors prior to submitting an application – further details will be provided.

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact.

We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).

_{AI_CDT_DecisionMaking}