QinetiQ
Imperial College London

AI-driven design of perovskite materials for clean energy technologies

Growing energy demand and depleting fossil fuels create an urgent need for sustainable energy solutions. Energy technologies are crucial for this transition and their progression relies on the development of advanced materials. Perovskites have emerged as highly promising material candidates for such devices due to their unique chemical and physical properties.

Perovskites are a class of material with the general formula ABX₃. They possess a highly flexible structure, and by precisely altering their chemical configuration, it is possible to design perovskite materials with enhanced properties for use in energy applications. However, with such a vast number of possible structures and configurations, testing all possibilities is not possible through conventional methods.

Cordelia’s project aims to harness artificial intelligence to accelerate perovskite discovery. By leveraging experimental datasets, machine learning, and generative materials design approaches, the research aims to develop novel methodologies for the design and optimisation of perovskite materials for use in clean energy technologies.

This research has the potential to significantly impact many industries worldwide, providing an accelerated pathway to the development of next-generation energy devices with enhanced efficiency and durability, and ultimately helping to drive the transition to a net-zero carbon economy.

Biography

Since graduating with a First in Chemical Engineering from the University of Edinburgh in 2022, Cordelia has been working in the Advanced Materials team at global technology company QinetiQ, where her research has focussed on the application of AI and machine learning methods for the design and discovery of novel materials. Alongside this role, Cordelia has pursued a part-time MPhil in Physics within the Molecular Engineering group at the University of Cambridge. Her thesis investigated the use of text and image mining tools for the automated extraction of chemical reaction data from scientific literature.