FastTrack: a fast method to evaluate mass transport in solid leveraging universal machine learning interatomic potential

TL;DR

This paper presents a rapid and accurate machine learning-based framework for evaluating atomic migration barriers in crystals, significantly speeding up computations while maintaining high accuracy, suitable for high-throughput materials screening.

Contribution

The authors develop a novel method combining ML force fields with energy surface sampling to efficiently compute migration barriers without predefined pathways, outperforming traditional DFT methods.

Findings

MLFF-derived barriers are within tens of meV of DFT and experimental values.

Achieves approximately 100 times speedup over DFT-NEB calculations.

Fine-tuning on specific data improves the accuracy of the ML models.

Abstract

We introduce a rapid, accurate framework for computing atomic migration barriers in crystals by combining universal machine learning force fields (MLFFs) with 3D potential energy surface sampling and interpolation. Our method suppresses periodic self interactions via supercell expansion, builds a continuous PES from MLFF energies on a spatial grid, and extracts minimum energy pathways without predefined NEB images. Across twelve benchmark electrode and electrolyte materials including LiCoO2, LiFePO4, and LGPS our MLFF-derived barriers lie within tens of meV of DFT and experiment, while achieving ~10^2 x speedups over DFT-NEB. We benchmark GPTFF, CHGNet, and MACE, show that fine-tuning on PBE/PBE+U data further enhances accuracy, and provide an open-source package for high-throughput materials screening and interactive PES visualization.