Department of Computational and Data Sciences
Department Seminar
Speaker : Prof. Krishna Garikipati, Professor of Aerospace and Mechanical Engineering, University of Southern California
Title : Bridging scales with Machine Learning: From first principles statistical mechanics to continuum phase field computations to study order-disorder transitions in LixCoO2
Date & Time: December 18th, 2025 (Thursday), 15:00 PM
Venue : # 102, CDS Seminar Hall
ABSTRACT
Lix {TM} O2 (TM={Ni, Co, Mn}) forms an important family of cathode materials for Li-ion batteries, whose performance is strongly governed by Li composition-dependent crystal structure and phase stability. Here, we use LixCoO2 (LCO) as a model system to benchmark a machine learning-enabled framework for bridging scales in materials physics. We focus on assemblies of thousands of atoms described by density functional theory-informed statistical mechanics to further drive continuum phase field studies of the dynamics of order-disorder transitions in LCO. Central to the scale bridging is the rigorous, quantitatively accurate, representation of the free energy density and chemical potentials of this material system by coarse-graining formation energies for specific atomic configurations. We develop physics- and data-driven active learning workflows to train integrable deep neural networks for such high-dimensional free energy density and chemical potential functions. Additionally, we explore Equivariant Graph Neural Networks to bypass traditional cluster expansion-based representations formation energies subsequently used in the statistical mechanics. The resulting, first principles-informed, machine learning-enabled, phase-field computations allow us to study LCO cathodes’ order-disorder transitions in terms of temperature, microstructure, and charge cycling. To the best of our knowledge, such a scale bridging framework has not been previously demonstrated for LCO, or for materials systems of comparable technological interest. This approach can be expanded to other materials systems and can incorporate additional physics to that studied here.
BIO: Krishna Garikipati obtained his PhD at Stanford University in 1996, and after a few years of post-doctoral work, he joined the University of Michigan in 2000, rising to Professor in the Departments of Mechanical Engineering and Mathematics. Between 2016 and 2022, he served as the Director of the Michigan Institute for Computational Discovery & Engineering (MICDE). In January 2024 he moved to the University of Southern California as a Professor of Aerospace and Mechanical Engineering. His research is in scientific machine learning and computational science, with applications drawn from biophysics, mathematical biology, materials physics and nonlinear mechanics. He has been awarded the DOE Early Career Award for Scientists and Engineers, the Presidential Early Career Award for Scientists and Engineers (PECASE), a Humboldt Research Fellowship, and the 2025 Oden Medal in Computational Science from the US Association for Computational Mechanics. He is a fellow of the US Association for Computational Mechanics, the International Association for Computational Mechanics and the Society of Engineering Science, a Life Member of Clare Hall at University of Cambridge, and a visiting scholar in Computational Biology at the Flatiron Institute of the Simons Foundation.
Host Faculty: Dr. Phani Motamarri
ALL ARE WELCOME
