Discovery of zero thermal expansion materials using Machine Learning and Advanced Data Analytics (Reference NSGZTEML2023)

   Department of Chemistry

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof M Rosseinsky, Dr M Dyer, Dr V Gusev  Applications accepted all year round  Funded PhD Project (Students Worldwide)

About the Project

Low and zero thermal expansion materials are used in many industries where size stability under high temperatures is critical e.g., aerospace, precision manufacturing, sensors. New classes of material are needed to meet intensifying future demands. There are considerable barriers to discovering the required materials. The underlying physics is complex and difficult to predict from first principles, and the space of possible materials is large and equally complex, especially when a combination of properties is needed, i.e., in this case zero thermal expansion and high machinability and durability. Machine learning methods have been successfully applied to many complex problems, and recent work has demonstrated such methods may also be viable to predict new functional materials with desirable properties. For example, neural networks and deep learning methods have attracted attention for their ability to consider complex combinations of multiple attributes/features in a nonlinear fashion to predict structured outputs. This PhD project will explore such methodologies as well as other machine learning and mathematical/statistical data analytics algorithms to model, predict and analyse various properties related to machinable zero thermal expansion materials.

Specifically, the student will work closely with computer scientists, inorganic chemists, physicists, and material scientists to develop tools to predict new materials that may exhibit zero thermal expansion combined with the desirable mechanical properties. This may involve developing models to identify new chemistries or regions of the periodic table where zero thermal expansion materials may occur, and/or identifying new ways to improve the required properties in existing materials. As a part of this goal, the student will work with both computed and experimental literature/database information to build models and descriptors to identify materials with the desired properties.

The machine learning and mathematical algorithms applied will go far beyond the conventional approaches deployed by physical computational science researchers thus far in the literature. This will be combined with the development of appropriate descriptors that use the team’s understanding of materials chemistry and physics together with the PhD candidate’s background and developing expertise in machine learning and artificial intelligence approaches.

The PhD position is part-funded by NSG Pilkington who are a leading manufacturer of glass for sustainable buildings, where materials are continuously exposed to high temperature environments during the manufacture and processing of glass products. The student will join a team of researchers working with NSG including synthetic chemists making the materials, materials scientists and computational chemists calculating stability and properties. This is thus a unique opportunity to develop and apply new deep learning methods to a technology problem as part of an integrated team working with a leading UK manufacturer.

Qualifications: Applications are welcomed from students with a 2:1 or higher master’s degree or equivalent in Computer Science, Chemistry, Physics, or Materials Science, particularly those with some of the skills directly relevant to the project outlined above. Successful candidates will have strong math and programming skills. An interest and/or coursework in condensed matter physics is a benefit, though not required.

Please apply by completing the online postgraduate research application form here: How to apply for a PhD - University of Liverpool

Please ensure you quote the following reference on your application: Discovery of zero thermal expansion materials using Machine Learning and Advanced Data Analytics (Reference NSGZTEML2023)

The award is 50% funded by NSG Group and 50% funded by the University of Liverpool through an EPSRC Doctoral Training Partnership award and will pay full tuition fees and a maintenance grant for 3.5 years. Applications from candidates meeting the eligibility requirements of the EPSRC are welcome – please refer to the EPSRC website ( It provides full tuition fees and a stipend of approx. £17,668 (this is the rate from 01/10/2022) full time tax free per year for living costs. The stipend costs quoted are for students starting from 1st October 2022 and will rise slightly each year with inflation.

The funding for this studentship also comes with a budget for research and training expenses of £1000 per year, and for those that are eligible, a disabled students allowance to cover the costs of any additional support that is required.

Due to a change in UKRI policy, this is now available for Home, EU or international students to apply. However, please be aware there is a limit on the number of international students we can appoint to these studentships per year.

You will be encouraged to undertake some teaching duties for the department for which you will receive training and payment. You will have the option to work towards and apply for Associate Fellowship of the Higher Education Academy (via the Foundations in Learning & Teaching in Higher Education (FLTHE) programme or the University of Liverpool Teaching Recognition and Accreditation (ULTRA) Framework

Please ensure you include the project title and quote CCPR084 on the application.

Chemistry (6) Mathematics (25)


1. Perspective on methods applied: Machine learning modelling of superconducting critical temperature. arXiv:1709.02727 [cond-mat.supr-con]
2. Prediction of Thermal Properties of Zeolites through Machine Learning, Journal of Physical Chemistry C, 126, 1651 (2022)
3. A machine learning approach to predict thermal expansion of complex oxides, Computational Materials Science, 210, 111034 (2022)
4. Web-based machine learning models for real-time screening of thermoelectric materials properties. APL Materials 4, 053213 (2016);

Where will I study?

 About the Project