DATA-DRIVEN DISCOVERY OF NEW MATERIALS FOR SOLIDSTATE BATTERIES

Mo Yifei
Department of Materials Science and Engineering,
University of Maryland, College Park, MD, USA.

EXTENDED ABSTRACT: All-solid-state Li-ion battery based on solid electrolytes is a promising nextgeneration battery technology with high energy density, intrinsic safety, long cycle life, and wide operational temperatures. However, the lack of solid electrolyte materials that satisfy multiple requirements, such as high ionic conductivity, good stability, and interfacial compatibility with the electrode, are impeding the development of this new battery technology. To resolve these materials challenges, we develop and leverage an array of data-driven computation techniques including machine learning to discover and design novel solid-state Li-ion conductors as solid electrolytes for all-solid-state batteries. The data-driven approach enables rapid searching over a large materials space of tens of thousands of materials with highly diverse structures and chemistries. Dozens of novel solid-state conductors are discovered through our data-driven materials search. Our data-driven analyses provide unique insights into the fundamental understanding about solid-state Li-ion conductors beyond traditional physical mechanistic studies. Our study demonstrates a new paradigm of using machine learning techniques for materials discovery that overcome the data-scarcity challenges.