A chemically inspired convolutional neural network using electronic structure representation

Abstract

In recent years, a development of appropriate crystal representations for accurate prediction of inorganic crystal properties has been considered as one of the essential tasks to accelerate materials discovery through...

Accelerating the Search for New Solid Electrolytes: Exploring Vast Chemical Space with Machine Learning-Enabled Computational Calculations

“…Despite their accuracies, they are not suitable for HTVS as they require relaxed structures to prepare input representations. Other approaches that require less or no information on geometries would be more appropriate for this purpose. − In this work, we expanded the chemical space, performed HTVS by applying different ML models to evaluate multiple properties, and identified several promising candidates for SEs.…”