High-Throughput Screening of Li Solid-State Electrolytes with Bond Valence Methods and Machine Learning

Li-based solid-state electrolyte materials enable safer, all-solid-state batteries, but the computational search for candidates with favorable stability and high Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. We present a high-throughput screening approach for identifying promising materials using a combination of bond-valence methods and graph neural networks. An ablation study involving geometric and bond-valence quantities reveals their relative importance in the training of graph neural networks, providing insight for future modeling of ionic conductivity in Li SSE. We identify 329 candidates with good stability and ionic conductivity, including 28 stable against Li metal. Furthermore, we combine the ML-accelerated screening procedure with an isovalent substitution scheme to generate and screen additional candidates beyond existing databases, identifying an additional 239 candidate materials for battery applications.