Machine Learning Modeling for Accelerated Battery Materials Design in the Small Data Regime

摘要

Machine learning (ML)-based approaches to battery design are relatively newbut demonstrate significant promise for accelerating the timeline for newmaterials discovery, process optimization, and cell lifetime prediction. Batterymodeling represents an interesting and unconventional application area forML, as datasets are often small but some degree of physical understandingof the underlying processes may exist. This review article provides discussionand analysis of several important and increasingly common questions:how ML-based battery modeling works, how much data are required, howto judge model performance, and recommendations for building modelsin the small data regime. This article begins with an introduction to ML ingeneral, highlighting several important concepts for small data applications.Previous ionic conductivity modeling efforts are discussed in depth as a casestudy to illustrate these modeling concepts. Finally, an overview of modelingefforts in major areas of battery design is provided and several areas forpromising future efforts are identified, within the context of typical small dataconstraints.