MSE Seminar: Shuwen Yue (Cornell CBE)

Physics-inspired machine learning potentials for thermodynamic and dynamic properties of electrolyte solutions

Understanding the interactions which governs aqueous electrolyte solution properties is essential to advancements in countless domains, from electrochemistry to biochemistry. While molecular simulations have been extensively applied to study these systems, conventional empirical force fields fail to accurately predict many thermodynamic and dynamic properties, indicating limitations in capturing the underlying physics. In this talk, I will present our efforts in developing machine-learning potentials fit to a first-principles derived potential energy surface that can overcome these deficiencies. Moreover, we investigate unique modes of local dynamics in electrolyte solutions which contribute to their collective behavior. I will also describe our efforts in applying these potentials to better understand how electrolytes behave in confined environments and at hydrophobic interfaces. These studies highlight applications of machine learning for molecular simulations to not only improve property predictions but also achieve greater physical interpretability.<

Bio:
Shuwen Yue is an assistant professor in the Robert F. Smith School of Chemical and Biomolecular Engineering at Cornell University. Her group focuses on the study of electrolytes at interfaces, in confinement, and in electrochemical systems using machine learning and molecular simulation approaches. She is a Scialog Fellow and awardee in sustainable minerals, metals, and materials and received an Affinito-Stewart Award from Cornell President’s Council of Cornell Women. She serves on the Early Career Board of the Journal of Chemical Theory & Computation, Early Career Representative for the AAAS Section M Engineering Steering Committee, and Liaison Director of the AIChE Computational Molecular Science and Engineering Forum. Shuwen received her Ph.D. from the Department of Chemical & Biological Engineering at Princeton University and postdoctoral training in the Department of Chemical Engineering at MIT.