Early prediction of ion transport properties in solid polymer electrolytes using machine learning and system behavior-based descriptors of molecular dynamics simulations

Abstract

Molecular dynamics simulations are useful tools to screen solid polymer electrolytes with suitable properties applicable in Li-ion batteries. However, due to the vast design space of solid polymer electrolytes, it is highly desirable to accelerate the discovery pipeline by reducing the computational time of ion transport properties from simulations. In this study, we show that with a judicious choice of descriptors, we are able to predict the equilibrium ion transport properties in LiTFSI-homopolymer systems within the first 0.5 ns of the production run of simulations. The new set of descriptors used in the current study includes the configuration of ion clusters and early time evolution of transport properties. Specifically, we find that descriptors that include information about ion clustering and dynamics of ion transport in the polymer environment outperform features extracted from only the molecular structure of the polymers. We show that these behavior-based descriptors have several advantages over polymer structure-based descriptors, as they encode system (polymer and salt) behavior rather than just the class of polymer and can be computed at any time point during the simulations. These characteristics increase the applicability of our descriptors to a wide range of polymer systems (e.g., co-polymers, blend of polymers, salt concentrations, and temperatures).