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

TL;DR

This paper introduces a transfer learning-based graph neural network model that accurately predicts ionic migration barriers in solids, significantly improving materials discovery for energy applications.

Contribution

The study develops a novel transfer learning approach with architectural modifications to enhance $E_m$ prediction accuracy across diverse materials.

Findings

MODEL-3 achieves R$^2$ of 0.703 and MAE of 0.261 eV.

Model distinguishes migration pathways and generalizes across chemistries.

Classifier identifies good ionic conductors with 80 ext% accuracy.

Abstract

Ionic mobility determines the rate performance of several applications, such as batteries, fuel cells, and electrochemical sensors and is exponentially dependent on the migration barrier ($E_m$), a difficult to measure/calculate quantity. Previous approaches to identify materials with high ionic mobility have relied on imprecise descriptors given the lack of generalizable models to predict $E_m$. Here, we present a graph neural network based architecture that leverages principles of transfer learning to efficiently and accurately predict $E_m$ across a diverse set of materials. We use a model pre-trained simultaneously on seven distinct bulk properties (labeled MPT), modify the MPT model to classify different migration pathways in a structure, and fine-tune (FT) on a manually-curated literature-derived dataset of 619 $E_m$ data points calculated with density functional theory. Importantly, our best-performing FT model (labeled MODEL-3) demonstrates substantial improvements in prediction accuracy compared to classical machine learning methods, graph models trained from scratch, and a universal machine learned interatomic potential, with a R$^2$ score of 0.703 and a mean absolute error of 0.261 eV on the test set. Notably, MODEL-3 is able to distinguish different migration pathways within a structure and also demonstrates excellent ability to generalize across intercalant compositions and chemistries. As a classifier, MODEL-3 exhibits 80\% accuracy and 82.8\% precision in identifying materials that are `good' ionic conductors (i.e., structures with $E_m <$0.65~eV). Thus, our work demonstrates the effective use of FT strategies and architectural modifications necessary for making swift and accurate $E_m$ predictions, which will be useful for materials discovery in batteries and for predicting other data-scarce material properties.