Optimal search strategies for automated, robotic material discovery

This position will remain open until a suitable candidate has been found.

New functional materials are central to society but they can be hard to find in the laboratory because of the astronomical search space that is defined by the available atomic and molecular building blocks. To address this, we have recently developed a unique mobile ‘robotic chemist’ that can search for new materials in an automated fashion. A video of our progress so far can be found here: https://youtu.be/ehjMBDFhZ5A

This new hardware raises interesting challenges in Data and Computer Sciences, for example, in defining the most effective search strategies, where the ‘best’ material will usually be the global minimum in a highly complex search space. There are also difficult questions about how much prior knowledge to incorporate in the search algorithms. As such, the aim of this PhD is to build the ‘brain’ that will power the robotic search hardware in the laboratory.

The project will utilize and improve over the state of the art techniques in Optimisation, Data Mining and Machine Learning, in particular, tools from Bayesian optimisation, Recommender Systems and Graphical Models will be applied.
The project forms part of the £10 M Leverhulme Research Centre for Functional Materials Design, and there will be multiple opportunities to interact with other members of that centre in a range of areas such as experimental chemistry, computational chemistry, robotics, algorithms, and artificial intelligence.

Environment: The studentship will be physically based in the Materials Innovation Factory (MIF), a new £82M research facility, and supervised Dr John Fearnley, Dr Vladimir Gusev, and Professor A. I. Cooper FRS (the MIF Academic Director). The studentship is funded by the Leverhulme Research Centre for Functional Materials Design, a £10 M, 10-year activity funded by the Leverhulme Trust.
Qualifications: Applications are welcomed from students with a 2:1 or higher master’s degree or equivalent in Computer Science/Mathematics. Good understanding of theory will be very helpful. Keen interest in applied research is a plus.

Informal enquiries should be addressed to John Fearnley
Please apply by completing the online postgraduate research application form.
Please ensure you quote the following reference on your application: LRCVG