Machine learning for the quantum description of actinide and fission product chemistry

A fully-funded 4-year SATURN CDT PhD position (at the standard UKRI rate of £21,805 p.a. plus £2000 p.a. enhancement) is available in the Department of Chemistry at Lancaster University, in collaboration with the School of Mathematical Sciences, the Nuclear Decommissioning Authority and the UK National Nuclear Laboratory. More details of the SATURN CDT can be found at: https://www.saturn-nuclear-cdt.manchester.ac.uk/

The effective management of spent nuclear fuel, comprising uranium, heavier actinides and fission products, is key to the future of nuclear power in the UK. Molecular-level quantum chemical simulations can aid in the understanding of the chemical behaviour of spent fuel, but require computationally demanding state of the art simulation techniques to achieve the required accuracy. Recent developments in machine learning, in particular the Atomic Cluster Expansion (ACE) and its extensions, offer an approach to overcome this limitation, providing a potential route to the quantitative simulation of dynamic chemical process of direct relevance to the nuclear fuel cycle.

This PhD project aims to develop simulation tools that bring predictive power to the molecular simulation of fundamental chemical processes underpinning the behaviour of spent nuclear fuel. The approach harnesses machine learning to construct interatomic interaction models trained on high-accuracy quantum chemical simulation data, providing a framework to incorporate their accuracy and transfer it into dynamic simulation models that are efficient enough to allow these processes to be described with predictive accuracy. Specific aims of this project include:

• Development of high-level quantum chemical datasets for aqueous actinide and fission-product systems
• Development of prototype machine-learned interatomic potentials trained on these data sets
• Validation of these model potentials and integration into open-source molecular simulation platforms
• Application of these models to case studies of direct industrial relevance

Alongside broad research and presentation skills, the successful candidate will develop:

• Expertise in the application of both static and dynamic quantum chemical simulations techniques
• Ability in the training and implementation of machine learning frameworks
• Proficiency in the use of High-Performance Computing platforms
• A thorough understanding of the nuclear power industry, and the role that chemical simulation plays

The successful candidate will demonstrate a strong interest in quantum chemical simulation, the application of machine learning to problems in the chemical sciences, enthusiasm to work in a multidisciplinary environment, willingness to learn, a collaborative attitude, and will possess good written and oral communication skills.

About SATURN

This PhD is based with the SATURN Centre for Doctoral Training. SATURN is made up form a consortium of NW Universities that include Manchester, Leeds, Liverpool, Lancaster, Sheffield and Strathclyde. The ethos of the programme is to recruit students from across STEM and give them the necessary skills and training to become a subject matter expert in the nuclear sector in either industry or academia. You will be recruited with a cohort of other researchers all looking at nuclear focused research but from across the breadth of the sector. Your training will include an introduction to nuclear course as well as opportunities to do a deep dive in the areas that really interest you. You will also have the opportunity to broaden your experience and skills by visiting internationally relevant facilities, having an industry secondment, undertaking leadership training, and involving yourself in outreach and public engagement activities. If this sounds like the sort of opportunity that you are looking for, we would love to hear from you.

Nuclear Boot Camp (Months 1 - 3)

The Bootcamp is based at Manchester. For any of our students based at a partner institutions SATURN can offer you accommodation in Manchester and cover the cost.

Eligibility

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

Before you apply

We strongly recommend that you contact the supervisors for this project before you apply. For informal enquiries, please contact Dr Andy Kerridge at a.kerridge@lancaster.ac.uk and/or Dr Maciej Buze at m.buze@lancaster.ac.uk

How to apply

Please complete the Enquiry Form to express your interest. We strongly recommend you contact the project supervisor after completing the form to speak to them about your suitability for the project.

If your qualifications meet our standard entry requirements, the CDT Admissions Team will send your enquiry form and CV to the named project supervisor.

Our application process can also be found on our website: here If you have any questions, please contact SATURN@manchester.ac.uk

Equality, diversity and inclusion

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).