Machine-Learning Approaches for the Discovery of Electrolyte Materials for Solid-State Lithium Batteries

Abstract

Solid-state lithium batteries have attracted considerable research attention for their potential advantages over conventional liquid electrolyte lithium batteries. The discovery of lithium solid-state electrolytes (SSEs) is still undergoing to solve the remaining challenges, and machine learning (ML) approaches could potentially accelerate the process significantly. This review introduces common ML techniques employed in materials discovery and an overview of ML applications in lithium SSE discovery, with perspectives on the key issues and future outlooks.

Merits and Demerits of Machine Learning of Ferroelectric, Flexoelectric, and Electrolytic Properties of Ceramic Materials

“…ML is essentially a fitting procedure of many experimental data as a function of many factors called descriptors [ 2 , 4 ]. It has been argued that a lack of interpretability in ML could be a severe problem in terms of the reliability of the predicted values as well as development in scientific research based on causality [ 2 , 4 , 5 , 6 , 7 , 8 ]. On the other hand, the excellent fitting procedure of experimental data by means of ML could result in more accurate predicted values compared to first principles calculations, which could have some intrinsic systematic error [ 9 ].…”

“…On the other hand, the excellent fitting procedure of experimental data by means of ML could result in more accurate predicted values compared to first principles calculations, which could have some intrinsic systematic error [ 9 ]. Furthermore, ML could be computationally more economical compared to first principles calculations and could save time and effort [ 2 , 7 , 10 , 11 ]. ML could also save expensive and time-consuming experiments [ 12 , 13 , 14 , 15 , 16 , 17 ].…”

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

“…Theoretical approaches to ionic conductivity have traditionally relied on direct methods, such as ab initio molecular dynamics (MD), − despite being notably time-consuming. In recent years, the field of materials science has experienced a growing interest in the application of machine learning (ML) approaches, − aimed at predicting properties based on the accumulated data. Consequently, several studies have applied various ML techniques to design potential SSEs. − For example, Fujimura et al performed the support vector regression to predict the ionic conductivity of LISICON .…”

“…In recent years, the field of materials science has experienced a growing interest in the application of machine learning (ML) approaches, − aimed at predicting properties based on the accumulated data. Consequently, several studies have applied various ML techniques to design potential SSEs. − For example, Fujimura et al performed the support vector regression to predict the ionic conductivity of LISICON . Artificial neural network modeling was used to predict the Li diffusion barrier for LiMXO 4 .…”