Application of Machine Learning Tools to guide Materials Discovery

The PhD position is funded by the Leverhulme Centre for Functional Materials Design at the University of Liverpool via the Leverhulme Trust. The centre aims to bring together chemical knowledge with state-of-the-art computer science and automated technologies to develop a new approach to revolutionize the design of functional materials at the atomic scale.

This is an opportunity to undertake one of our new and exciting cross-disciplinary projects lying at the interface between materials chemistry and computer science. The ideal candidate would have strong problem solving and programming skills gained through a degree in computer science, chemistry, physics, maths or engineering.

We have a number of different problems to be investigated and the projects intend to develop new learning and optimisation techniques, theories and practical applications. Chemical applications may involve the discovery of better materials for automobile catalytic converters, industrial catalysis, transparent computer displays, new batteries and superconductors, and improving next generation manufacturing. The material discovery process is difficult because of the vast number of possible combinations of the components that can potentially be used to make a material. For example, for a single material class of metal-organic frameworks, over 90,000 materials have been reported so far with practically unlimited number of potential materials arising from combining various metal and organic ligands together. That is why crystal structure prediction [1], computational screening for materials properties [2] and machine learning predictions [3] play an important role in identifying most promising experimental targets. At the same time, these approaches are still under active development due to inherent fundamental challenges. By using the information already available about materials and developing approaches to quantify similarity between them, it is possible to narrow down the options for potential applications of a known or a hypothetical material as well. The projects can tackle knowledge extraction from materials databases as well as feature design and  representation learning to prioritise future experimental work.

The successful applicant will work closely with our strong teams of computational chemists, computer scientists, inorganic chemists, physicists and material scientists to develop ways of predicting and analysing new materials. Our success arises from a close working relationship between computational and experimental researchers within the group, which is part of the Leverhulme Centre for Functional Materials Design (https://www.liverpool.ac.uk/leverhulme-research-centre/), where researchers with physical science, engineering and computer science backgrounds collaborate closely. The successful candidate will work in this cross-disciplinary environment, using their computational skills in close collaboration with the experimental expertise within the research group, to accelerate the discovery of new functional materials.

Applications are welcomed from students with a 2:1 or higher master’s degree or equivalent in Chemistry, Physics, or Materials Science, particularly those with some of the skills directly relevant to the project outlined above.

To apply for this opportunity, please visit: https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/ Please quote reference CCPR014 in the funding section of the online application form.

For any enquiries please contact: Dr Dmytro Antypov (antypov@liverpool.ac.uk) or Dr Vladimir Gusev (Vladimir.Gusev@liverpool.ac.uk)