Machine Learning Prediction Models for Solid Electrolytes based on Lattice Dynamics Properties

TL;DR

This paper develops machine learning models incorporating dynamic lattice properties to accurately predict ionic conductivity in solid electrolytes, aiding the discovery of new superionic conductors.

Contribution

It introduces phonon-related dynamic features into ML models for solid electrolyte prediction, improving accuracy over static-parameter approaches.

Findings

Logistic regression classifier achieves 93% accuracy.

Random forest model has RMSE of 1.179 S/cm and R^2 of 0.710.

Screened 264 materials, identifying 11 promising superionic conductors.

Abstract

Recently, machine-learning approaches have accelerated computational materials design and the search for advanced solid electrolytes. However, the predictors are currently limited to static structural parameters, which may not fully account for the dynamic nature of ionic transport. In this study, we meticulously curated features considering dynamic properties and developed machine-learning models to predict the ionic conductivity of solid electrolytes. We compiled 14 phonon-related descriptors from first-principles phonon calculations along with 16 descriptors related to structure and electronic properties. Our logistic regression classifiers exhibit an accuracy of 93 %, while the random forest regression model yields a root mean square error of 1.179 S/cm and $R^2$ of 0.710. Notably, phonon-related features are essential for estimating the ionic conductivity in both models. Furthermore, we applied our prediction model to screen 264 Li-containing materials and identified 11 promising candidates as potential superionic conductors.