Exploring structure diversity in atomic resolution microscopy with graph neural networks

TL;DR

This paper introduces a graph neural network framework for analyzing diverse atomic structures in microscopy images, offering improved robustness, efficiency, and interpretability over traditional image-based deep learning models.

Contribution

The study presents a novel equivariant graph neural network approach for atomic structure analysis, significantly reducing parameters and enhancing flexibility compared to existing image-driven models.

Findings

Achieved three orders of magnitude reduction in model parameters.

Demonstrated robustness in analyzing vacancy lines with lattice distortions.

Enabled discovery of new doping configurations with enhanced electrocatalytic properties.

Abstract

The emergence of deep learning (DL) has provided great opportunities for the high-throughput analysis of atomic-resolution micrographs. However, the DL models trained by image patches in fixed size generally lack efficiency and flexibility when processing micrographs containing diversified atomic configurations. Herein, inspired by the similarity between the atomic structures and graphs, we describe a few-shot learning framework based on an equivariant graph neural network (EGNN) to analyze a library of atomic structures (e.g., vacancies, phases, grain boundaries, doping, etc.), showing significantly promoted robustness and three orders of magnitude reduced computing parameters compared to the image-driven DL models, which is especially evident for those aggregated vacancy lines with flexible lattice distortion. Besides, the intuitiveness of graphs enables quantitative and straightforward extraction of the atomic-scale structural features in batches, thus statistically unveiling the self-assembly dynamics of vacancy lines under electron beam irradiation. A versatile model toolkit is established by integrating EGNN sub-models for single structure recognition to process images involving varied configurations in the form of a task chain, leading to the discovery of novel doping configurations with superior electrocatalytic properties for hydrogen evolution reactions. This work provides a powerful tool to explore structure diversity in a fast, accurate, and intelligent manner.