Recent Advances in Screening Lithium Solid-State Electrolytes Through Machine Learning

Compared to the liquid electrolyte, lithium solid-state electrolytes have obtained increasing attention for all-solid-state lithium ion battery on account of the safety requirement and higher energy density. However, many challenges remained in the solid-state electrolytes such as lower ionic conductivity, complex interface and unstable physical or electrochemical properties. One of the effective strategies is finding new type of lithium solid-state electrolytes with improved properties. The traditional trial and error methods acquire a lot of resources and time to verify the new solid-state electrolyte. Recently, some new lithium solid-state electrolytes were predicted through machine learning (ML), which has been proved to be an efficient and reliable method for screening new functional materials. This paper reviews the recent process of lithium solid-state electrolytes discovered based on ML algorithm. The selection and preprocessing of the datasets in ML technology are illustrated initially, and then the latest developments in screening lithium solid-state electrolytes through different ML algorithm are summarized and discussed in detail. Lastly, the stability of the candidate solid-state electrolyte and the challenges in discovering new lithium solid-state electrolytes through ML are highlighted.