| COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Engineering - Mechanics Colloquia Research Seminars > Material Discovery via Machine Learning and Research Lab Automation
Material Discovery via Machine Learning and Research Lab AutomationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact div-c. The discovery of functional materials is often hindered by vast compositional search spaces, complex structure-property relationships, and labour-intensive experimental workflows. In this talk, I present a data-driven framework that unites machine learning (ML), automated synthesis, and high-throughput characterisation to accelerate the exploration of disordered and dielectric perovskite materials for wireless communication and biosensing applications. At the core of this approach is a robotic materials discovery platform capable of ML-guided candidate selection, rapid sintering, and GHz-range dielectric property evaluation, reducing the experimental cycle from days to minutes. Complementing this experimental advance, we introduce a formula graph-based self-attention neural network that bridges stoichiometry-only and structure-informed descriptors for property prediction. This hybrid model exhibits strong generalizability, enabling the discovery of complex materials such as those with epsilon-near-zero behaviour. Furthermore, we explore unsupervised learning strategies to extract interpretable fingerprints of disorder, crystal symmetry, and perovskite formability directly from chemical composition. These embeddings underpin a scalable analogue-based recommendation engine that has successfully mined over 600,000 hypothetical compositions with a >90% hit rate. Professor Yang Hao is the QinetiQ/Royal Academy of Engineering Research Chair at Queen Mary University of London. His work has been recognized both nationally and internationally through his books “Antennas and Radio Propagation for Body-Centric Wireless Communications” and “FDTD Modeling of Metamaterials: Theory and Applications” (Artech House, USA ), as well as through highly cited papers published in leading journals, including Nature Communications, Advanced Science, Physical Review Letters, Applied Physics Letters, IEEE Proceedings, and Transactions. His research on transformation optics and metamaterials has led to many tangible benefits for a range of industrial products. One example is metalens antenna designs for satellite communications. This technology has been fully scoped and is currently being commercialised by the startup Isotropic System Limited (All.Space). Prof. Hao has won many accolades, including the prestigious IEEE John Kraus Antenna Award, the European EurAAP Antenna Award, the AF Harvey Research Prize, the BAE Chairman’s Silver Award, and the Royal Society Wolfson Research Merit Award. He was an AdCom Member and currently serves as the Chair of the Publication Committee for the IEEE Antennas and Propagation Society. Prof. Hao is an elected Fellow of the Royal Academy of Engineering, IEEE , and IET . This talk is part of the Engineering - Mechanics Colloquia Research Seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsDAMTP Fluids Talks Gates Cambridge Annual Lecture 7 March 2017 Public Understanding of RiskOther talksA retelling of the Quantum Mechanics story The public speaks back: health communication in Britain, 1980s-2020. **PLEASE NOTE CHANGE OF TIME AND LOCATION** The Long Way to Intersection Theory -- Mathematical Politics about Space Curves from Max Noether to the 1990s Insights into mental health disorders from genetics and immunology Friends, neighbours and enemies: cell-to-cell communication in times of stress |