FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Probabilistic programming for discovery of sustainable materials

   School of Electrical Engineering, Electronics and Computer Science

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

Click here to search for PhD studentship opportunities
  Prof Rahul Savani, Prof M J Rosseinsky, Dr V Gusev, Dr M Gaultois, Dr Dmytro Antypov  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

This position will remain open until a suitable candidate has been found so early applications are recommended.

In this project, we aim to develop probabilistic machine learning models such as belief networks and variational autoencoders to revolutionize materials discovery. Probabilistic approaches can naturally handle uncertainty in the measured data and modelling, and lead to generative methods which will allow prediction of truly novel materials with exotic properties. This machinery will be combined with the development of appropriate descriptors and architectures that use the team’s understanding of materials chemistry, physics, and computer science.

New materials are key drivers for societal benefit. They underpin technologies that tackle the global challenges of climate change and resource sustainability and open up new scientific phenomena and understanding. To access new materials is to traverse a vast and complex space of chemical composition, structural arrangement, chemical bonding and electronic structure, while understanding the experimental conditions needed to prepare the materials. Discovering revolutionary materials is thus incredibly challenging, but developments in artificial intelligence and machine learning promise to accelerate traditional approaches.

Specifically, the student will work closely with computer scientists, inorganic chemists, physicists, and material scientists to develop tools to predict new materials with favourable properties for new technologies, such as batteries and high-temperature superconductors. This may involve developing models to identify new chemistries or regions of the periodic table where superconducting states may occur, and/or identifying new ways to improve Li-ion conductivity in existing materials. As a part of this goal, the student will build models and descriptors to identify shared features in known materials that correlate strongly with the presence of properties favourable for high temperature superconductors, batteries, thermoelectrics, photovoltaics, or transparent conductors.

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.

Applications from candidates meeting the eligibility requirements of the EPSRC are welcome – please refer to EPSRC website:  

Students are encouraged to undertake some teaching duties for the Department, up to a maximum of 6 hours per week in term time, for which they will receive training and be paid at the regular hourly rate (currently £15.99 per hour). 

Informal enquiries should be addressed to Prof Rahul Savani [Email Address Removed]

Please apply by completing the online postgraduate research application form here:  Please ensure you quote the following reference on your application: Discovery of high-temperature superconductors using Deep Learning (Reference LRC1903CS)

Funding Notes

The award is primarily available to UK students and will pay full tuition fees and a maintenance grant for 42 months (£15,609 for 2021/2022). EU and non-EU students are eligible to apply but would need to have their own funding to cover the difference between the UK and international tuition fees. Please refer to our Fees and Funding webpage


Probabilistic machine learning and artificial intelligence. Nature 521, 452--459 (2015);
Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry. Nature Communications vol. 12, Article number 5561 (2021)
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs