Guaranteed Structure Prediction with Machine Learning

New materials are urgently needed to address global challenges our society faces today. The atomistic structure dictates their stability and properties. Structure prediction is difficult due to the quantum nature of interatomic interactions and the combinatorial explosion of possible arrangements of atoms. Classical force-fields and heuristic optimisation methods are typically used to overcome these challenges.

In a recent breakthrough [1], we developed a mathematical optimisation approach based on integer programming to structure prediction that provides guaranteed outcomes and offers new ways of addressing combinatorial explosion. However, it relies on force-fields for predictions, which are often chemistry specific and have limited fidelity. Recently, interatomic potentials based on machine learning have emerged as the main avenue to address these issues.

In this project, we will expand our approach and make machine learning part of the optimisation routine. This includes simultaneous use of interatomic interaction and property prediction models. High-fidelity assessment of stability and properties with guarantees across the periodic table will provide a unique capability in material science. The student will contribute to trustworthy and verifiable AI in science and gain transferable skills in combining machine learning with optimisation. The project is multi-disciplinary, and we specifically welcome students with backgrounds in mathematics, physics, chemistry, engineering, and computer science.

This project will be supervised by Dr Vladimir Gusev (Dept. Computer Science) and Prof Matthew Rosseinsky (Dept. Chemistry). Any informal enquiries about the project can be directed to Vladimir.Gusev@liverpool.ac.uk.

The global need for researchers with capabilities in materials chemistry, digital intelligence and automation is intensifying because of the growing challenge posed by Net Zero and the need for high-performance materials across multiple sectors. The disruptive nature of recent advances in artificial intelligence (AI), robotics, and emerging quantum computing offers timely and exciting opportunities for PhD graduates with these skills to make a transformative impact on both R&D and society more broadly.

The University of Liverpool EPSRC Centre for Doctoral Training in Digital and Automated Materials Chemistry is therefore offering multiple studentships for students from backgrounds spanning the physical and computer sciences to start in October 2025. These students will develop core expertise in robotic, digital, chemical and physical thinking, which they will apply in their domain-specific research in materials design, discovery and processing. By working with each other and benefiting from a tailored training programme they will become both leaders and fully participating team players, aware of the best practices in inclusive and diverse R&D environments.

This training is based on our decade-long development of shared language and student supervision between the physical, engineering and computer sciences, and takes place in the Materials Innovation Factory (MIF), the largest industry-academia colocation in UK physical science. The training content has been co-developed with 35 industrial partners and is designed to generate flexible, employable, enterprising researchers who can communicate across domains.

Applicant Eligibility

Candidates will have, or be due to obtain, a Master’s Degree or equivalent related to Physical Science, Engineering or Computational Science. Exceptional candidates with a First Class Bachelor’s Degree in an appropriate field will also be considered.

Application Process

Applicants are advised to apply as soon as possible no later than 17^th February 2025. The CDT will hold two rounds of applications assessment:

·      Assessment Round 1: for all applications received between 11^th December 2024 – 15^th January 2025.

·      Assessment Round 2: for all applications received between 16^th January 2025 – 17^th February 2025

Applicants who wish to be considered in Assessment Round 1 must apply by 15^th January 2025. Projects will be closed when suitable candidate has been identified (this could be before the 17th February 2025 deadline).

Please review our guide on “How to Apply” carefully and complete the online postgraduate research application form to apply for this PhD project in Computer Science.

We strongly encourage candidates to get in touch with the supervisory team to get a better idea of the project.

We want all our Staff and Students to feel that Liverpool is an inclusive and welcoming environment that actively celebrates and encourages diversity. We are committed to working with students to make all reasonable project adaptations including supporting those with caring responsibilities, disabilities or other personal circumstances. For example, if you have a disability you may be entitled to a Disabled Students Allowance on top of your studentship to help cover the costs of any additional support that a person studying for a doctorate might need as a result.