期刊
COMPUTATIONAL MATERIALS SCIENCE
卷 231, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.commatsci.2023.112535
关键词
Structural analysis; Descriptor; Deep learning; Molecular dynamics; Crystalline structure; Amorphous state
Accurate structural analysis is crucial for understanding atomic-scale processes in materials, but traditional methods often face limitations when applied to systems with thermal fluctuations or defect-induced distortions. To address this, the authors propose a novel descriptor for encoding atomic environments into 2D images, which enables accurate analysis using Convolutional Neural Networks at a low computational cost.
Accurate structural analysis is essential to gain physical knowledge and understanding of atomic-scale processes in materials from atomistic simulations. However, traditional analysis methods often reach their limits when applied to crystalline systems with thermal fluctuations, defect-induced distortions, partial vitrification, etc. In order to enhance the means of structural analysis, we present a novel descriptor for encoding atomic environments into 2D images, based on a pixelated representation of graph-like architecture with weighted edge connections of neighboring atoms. This descriptor is well adapted for Convolutional Neural Networks and enables accurate structural analysis at a low computational cost. In this paper, we showcase a series of applications, including the classification of crystalline structures in distorted systems, tracking phase transformations up to the melting temperature, and analyzing liquid-to-amorphous transitions in pure metals and alloys. This work provides the foundation for robust and efficient structural analysis in materials science, opening up new possibilities for studying complex structural processes, which cannot be described with traditional approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据