Discovery of Unconventional Proton-Conducting Inorganic Solids via Defect-Chemistry-Trained, Interpretable Machine Learning

High-throughput computational screening and machine learning hold significant potential for exploring diverse chemical compositions and discovering novel inorganic solids. However, the complexity of point defects, which occur in all inorganic solids and are often crucial to their functionality and synthesizability, presents significant challenges. Here, this study presents a defect-chemistry-trained, interpretable machine learning approach, designed to accelerate the exploration and discovery of unconventional proton-conducting inorganic solid electrolytes. By considering dopant dissolution and hydration reactions, the machine learning models provide quantitative predictions and physical interpretations for synthesizable host-dopant combinations with hydration capabilities across various structures. Utilizing these insights, two unconventional proton conductors, Pb-doped Bi12SiO20 sillenite and eulytite-type Sr-doped Bi4Ge3O12, are discovered in the first two synthesis trials. Notably, the Pb-doped Bi12SiO20 represents an unprecedented class of proton-conducting electrolyte composed solely of groups 14 and 15 cations and featuring a sillenite structure. It exhibits unique and fast 3D proton conduction along a loosely bonded BiO5 network. This study demonstrates an efficient approach for exploring novel inorganic materials. Point defects, ubiquitous in all inorganic solids, play crucial roles in both their functionality and synthesizability. Here, ab initio datasets are employed to develop defect-chemistry-trained, interpretable machine learning models for proton-conducting inorganic solid electrolytes. These models provide generalized insights into dopant dissolution and hydration, leading to the discovery of two unconventional proton conductors, Pb-doped Bi12SiO20 and Sr-doped Bi4Ge3O12.image

Automated summary

This study presents a machine learning approach to accelerate the exploration and discovery of unconventional proton-conducting inorganic solid electrolytes. By considering dopant dissolution and hydration reactions, the machine learning models provide quantitative predictions and physical interpretations for synthesizable host-dopant combinations with hydration capabilities. Utilizing these insights, two unconventional proton conductors are discovered. This study demonstrates an efficient approach for exploring novel inorganic materials.