Defect detection in atomic-resolution images via unsupervised learning with translational invariance

Abstract Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yueming Guo, Sergei V. Kalinin, Hui Cai, Kai Xiao, Sergiy Krylyuk, Albert V. Davydov, Qianying Guo, Andrew R. Lupini
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/4ad377f4cfce4a508ea0aa5446612074
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4ad377f4cfce4a508ea0aa5446612074
record_format	dspace
spelling	oai:doaj.org-article:4ad377f4cfce4a508ea0aa54466120742021-11-14T12:15:31ZDefect detection in atomic-resolution images via unsupervised learning with translational invariance10.1038/s41524-021-00642-12057-3960https://doaj.org/article/4ad377f4cfce4a508ea0aa54466120742021-11-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00642-1https://doaj.org/toc/2057-3960Abstract Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can continue over very long periods. Automatic detection and classification of defects in the STEM images are needed in order to handle the data in an efficient way. However, like many other tasks related to object detection and identification in artificial intelligence, it is challenging to detect and identify defects from STEM images. Furthermore, it is difficult to deal with crystal structures that have many atoms and low symmetries. Previous methods used for defect detection and classification were based on supervised learning, which requires human-labeled data. In this work, we develop an approach for defect detection with unsupervised machine learning based on a one-class support vector machine (OCSVM). We introduce two schemes of image segmentation and data preprocessing, both of which involve taking the Patterson function of each segment as inputs. We demonstrate that this method can be applied to various defects, such as point and line defects in 2D materials and twin boundaries in 3D nanocrystals.Yueming GuoSergei V. KalininHui CaiKai XiaoSergiy KrylyukAlbert V. DavydovQianying GuoAndrew R. LupiniNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Yueming Guo Sergei V. Kalinin Hui Cai Kai Xiao Sergiy Krylyuk Albert V. Davydov Qianying Guo Andrew R. Lupini Defect detection in atomic-resolution images via unsupervised learning with translational invariance
description	Abstract Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can continue over very long periods. Automatic detection and classification of defects in the STEM images are needed in order to handle the data in an efficient way. However, like many other tasks related to object detection and identification in artificial intelligence, it is challenging to detect and identify defects from STEM images. Furthermore, it is difficult to deal with crystal structures that have many atoms and low symmetries. Previous methods used for defect detection and classification were based on supervised learning, which requires human-labeled data. In this work, we develop an approach for defect detection with unsupervised machine learning based on a one-class support vector machine (OCSVM). We introduce two schemes of image segmentation and data preprocessing, both of which involve taking the Patterson function of each segment as inputs. We demonstrate that this method can be applied to various defects, such as point and line defects in 2D materials and twin boundaries in 3D nanocrystals.
format	article
author	Yueming Guo Sergei V. Kalinin Hui Cai Kai Xiao Sergiy Krylyuk Albert V. Davydov Qianying Guo Andrew R. Lupini
author_facet	Yueming Guo Sergei V. Kalinin Hui Cai Kai Xiao Sergiy Krylyuk Albert V. Davydov Qianying Guo Andrew R. Lupini
author_sort	Yueming Guo
title	Defect detection in atomic-resolution images via unsupervised learning with translational invariance
title_short	Defect detection in atomic-resolution images via unsupervised learning with translational invariance
title_full	Defect detection in atomic-resolution images via unsupervised learning with translational invariance
title_fullStr	Defect detection in atomic-resolution images via unsupervised learning with translational invariance
title_full_unstemmed	Defect detection in atomic-resolution images via unsupervised learning with translational invariance
title_sort	defect detection in atomic-resolution images via unsupervised learning with translational invariance
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/4ad377f4cfce4a508ea0aa5446612074
work_keys_str_mv	AT yuemingguo defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT sergeivkalinin defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT huicai defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT kaixiao defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT sergiykrylyuk defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT albertvdavydov defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT qianyingguo defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance AT andrewrlupini defectdetectioninatomicresolutionimagesviaunsupervisedlearningwithtranslationalinvariance
_version_	1718429344258326528

Defect detection in atomic-resolution images via unsupervised learning with translational invariance

Ejemplares similares