Overview
This project combines explainable AI and robotic solid-state synthesis to accelerate the discovery of new materials. You will synthesise materials with new crystal structures by targeting promising chemical spaces guided by automated reasoning tools. The work develops skills in automation, programming, solid-state synthesis and crystallography, within an interdisciplinary team combining computational and experimental expertise.
About this opportunity
New properties require new structures. Chemical understanding has guided us to the materials underpinning the technologies we use every day. But with growing global challenges, we need to find these new structural families faster. This synthesis project will discover these materials, with synthetic target and method selection guided by explainable AI methods recently developed by the supervisory team. These automated reasoning tools (Angewandte Chemie 2025, 64, e202417657) will allow you to explore the consequences of your chemical understanding to identify the most suitable regions of chemical space for synthesis that leads to new structural families. Exploration of these predictions will be accelerated with a robotic workflow for solid state chemistry, integrating automated weighing and mixing with high temperature furnaces to perform reactions and automated diffraction with AI data analysis.
The project will allow the student to develop expertise in automation and programming (including both using and extending the explainable AI frameworks) as well as solid state synthesis, crystallography and measurement techniques. The student will develop a common language across the areas of automation, AI and chemical synthesis, acquiring skills in teamwork, scientific communication and interdisciplinary working as computational and experimental researchers within the team work closely together.
The project is based on a new materials family recently discovered in Liverpool. This family is unique as it reaches the structural complexity level of the most complex minerals while retaining cubic symmetry. As it is out-of-distribution, only explainable methods will allow AI to assist humans in building on it, and the team’s specialist focus on explainable AI methods offer an opportunity for immersion in this topic.
This project will be supervised by Prof Matthew Rosseinsky OBE FRS (Department of Chemistry) and Prof Katie Atkinson (Department of Computer Science and Informatics). The supervisory team combines experts in inorganic materials discovery, synthesis and characterisation accelerated with digital workflows (Prof Rosseinsky) with expertise in interpretable AI tools applied to chemistry and beyond (Prof Atkinson). The automated synthesis workflow has been developed in the group, and. AI tools for pre-synthesis identification of target compositional phase fields have been developed in collaboration between Prof Rosseinsky and Prof Atkinson specifically to integrate into autonomous workflows. The student will work in a team that has a proven track record of integrating synthetic chemistry, computation and AI to discover new functional materials (Science 2024, 383, 739), providing an excellent training environment.
This project is expected to start in October 2026 and is offered under the EPSRC Centre for Doctoral Training in Digital and Automated Materials Chemistry based in the Materials Innovation Factory at the University of Liverpool, the largest industry-academia colocation in UK physical science. The successful candidate will benefit from training in robotic, digital, chemical and physical thinking, which they will apply in their domain-specific research in materials design, discovery and processing. PhD training has been developed with 35 industrial partners and is designed to generate flexible, employable, enterprising researchers who can communicate across domains.