Early Prediction of Ion Transport Properties in Solid Polymer Electrolytes Using Machine Learning and System Behavior-Based Descriptors of Molecular Dynamics Simulations

Molecular dynamics simulations are useful tools to screensolidpolymer electrolytes with suitable properties applicable to Li-ionbatteries. However, due to the vast design space of polymers, it ishighly desirable to accelerate the screening by reducing the computationaltime of ion transport properties from simulations. In this study,we show that with a judicious choice of descriptors we can predictthe equilibrium ion transport properties in LiTFSI-homopolymersystems within the first 0.5 ns of the production run of simulations.Specifically, we find that descriptors that include information aboutthe behavior of the system, such as ion clustering and time evolutionof ion transport properties, have several advantages over polymerstructure-based descriptors, as they encode system (polymer and salt)behavior rather than just the class of polymers and can be computedat any time point during the simulations. These characteristics increasethe applicability of our descriptors to a wide range of polymer systems(e.g., copolymers, blend of polymers, salt concentrations, and temperatures)and can be impactful in significantly shortening the discovery pipelinefor solid polymer electrolytes.

Automated summary

Molecular dynamics simulations are useful for screening solid polymer electrolytes for Li-ion batteries. This study shows that by using suitable descriptors, we can predict ion transport properties in LiTFSI-homopolymer systems within a short simulation time, which can greatly accelerate the discovery process for solid polymer electrolytes.