Learning Atomic Structure and Properties with Machine Learning by Assistant Professor Christopher Sutton

NTU MSE Seminar Hosted by Associate Professor Kedar Hippalgaonkar

Abstract

Advances in materials science that drive technological innovation require a quantitative understanding of atomic-scale phenomena and the chemical and physical processes that govern them. The predictive design of materials for targeted applications further depends on identifying stable compositions, their crystal structures, and the resulting properties. A central challenge in computational materials science is therefore the development of accurate predictive models that bridge quantum mechanical calculations with experimental observations.

In this talk, I will highlight recent advances in applying quantum mechanics and machine learning to design and understand materials (with an emphasis on accelerating the development of materials for energy storage and conversion). In particular, I will present our work on machine learning interatomic potentials to predict the structures of new materials, including hybrid organic soft-lattice semiconductors, and to provide atomistic insights into complex systems such as next-generation Li-ion battery anodes. 

I will also discuss our recent work on generative models for materials discovery. While generative models have demonstrated remarkable success in generating realistic crystal and molecular structures from noisy initial configurations, we are extending them to identify transition states and reaction pathways in heterogeneous catalysis.

Abstract


Assistant Professor Christopher Sutton
University of Toronto

Chris Sutton received his Ph.D. from the Georgia Institute of Technology and then joined the Fritz Haber Institute of the Max Planck Society in Berlin as an Alexander von Humboldt Postdoctoral Fellow. In 2021, he joined the University of South Carolina as an Assistant Professor. He joined the University of Toronto in 2025, where he is an Assistant Professor in the Department of Materials Science and Engineering and a Faculty Advisor in the Acceleration Consortium.