Leveraging transfer learning for accurate estimation of ionic migration barriers in solids

Abstract Rate performance of several applications, such as batteries, fuel cells, and electrochemical sensors, is exponentially dependent on the ionic migration barrier ( E m ) within solids, a difficult-to-estimate quantity. Previous approaches to identify materials with low E m have often relied on imprecise descriptors or rules-of-thumb. Here, we present a graph-neural-network-based architecture that leverages principles of transfer learning to efficiently and accurately predict E m across a variety of materials. We use a model (labeled MPT) that has been simultaneously pre-trained on seven bulk properties, introduce architectural modifications to build inductive bias on different migration pathways in a structure, and subsequently fine-tune (FT) on a manually-curated, literature-derived, first-principles computational dataset of 619 E m values. Importantly, our best-performing FT model (labeled MODEL-3, based on test set scores) demonstrates substantially better accuracy compared to classical machine learning methods, graph models trained from scratch, and a universal machine learned interatomic potential, with a R 2 score and a mean absolute error of 0.703 ± 0.109 and 0.261 ± 0.034 eV, respectively, on the test set and is able to classify ‘good’ ionic conductors with an 80% accuracy. Thus, our work demonstrates the effective use of FT strategies and MPT architectural modifications to predict E m , and can be extended to make predictions on other data-scarce material properties.