Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Zheng, Feng, Ming, Gao, Zijian, Yu, Jinyang, Hu, Liang, Wang, Tao, Xue, Shenao, Zhou, Shen, Ouyang, Fangping, Feng, Dawei, Xu, Kele, Wang, Shanshan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.17631
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910662978961408
author Luo, Zheng
Feng, Ming
Gao, Zijian
Yu, Jinyang
Hu, Liang
Wang, Tao
Xue, Shenao
Zhou, Shen
Ouyang, Fangping
Feng, Dawei
Xu, Kele
Wang, Shanshan
author_facet Luo, Zheng
Feng, Ming
Gao, Zijian
Yu, Jinyang
Hu, Liang
Wang, Tao
Xue, Shenao
Zhou, Shen
Ouyang, Fangping
Feng, Dawei
Xu, Kele
Wang, Shanshan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17631
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring structure diversity in atomic resolution microscopy with graph neural networks
Luo, Zheng
Feng, Ming
Gao, Zijian
Yu, Jinyang
Hu, Liang
Wang, Tao
Xue, Shenao
Zhou, Shen
Ouyang, Fangping
Feng, Dawei
Xu, Kele
Wang, Shanshan
Materials Science
Mesoscale and Nanoscale Physics
Machine Learning
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.
title Exploring structure diversity in atomic resolution microscopy with graph neural networks
topic Materials Science
Mesoscale and Nanoscale Physics
Machine Learning
url https://arxiv.org/abs/2410.17631