Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

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

Abstract

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.

Authors:
; ORCiD logo; ; ORCiD logo; ; ORCiD logo; ; ORCiD logo
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1829523
Alternate Identifier(s):
OSTI ID: 1831665
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Published Article
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Name: npj Computational Materials Journal Volume: 7 Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Country of Publication:
United Kingdom
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Guo, Yueming, Kalinin, Sergei V., Cai, Hui, Xiao, Kai, Krylyuk, Sergiy, Davydov, Albert V., Guo, Qianying, and Lupini, Andrew R. Defect detection in atomic-resolution images via unsupervised learning with translational invariance. United Kingdom: N. p., 2021. Web. doi:10.1038/s41524-021-00642-1.
Copy to clipboard
Guo, Yueming, Kalinin, Sergei V., Cai, Hui, Xiao, Kai, Krylyuk, Sergiy, Davydov, Albert V., Guo, Qianying, & Lupini, Andrew R. Defect detection in atomic-resolution images via unsupervised learning with translational invariance. United Kingdom. https://doi.org/10.1038/s41524-021-00642-1
Copy to clipboard
Guo, Yueming, Kalinin, Sergei V., Cai, Hui, Xiao, Kai, Krylyuk, Sergiy, Davydov, Albert V., Guo, Qianying, and Lupini, Andrew R. Tue . "Defect detection in atomic-resolution images via unsupervised learning with translational invariance". United Kingdom. https://doi.org/10.1038/s41524-021-00642-1.
Copy to clipboard
@article{osti_1829523,
title = {Defect detection in atomic-resolution images via unsupervised learning with translational invariance},
author = {Guo, Yueming and Kalinin, Sergei V. and Cai, Hui and Xiao, Kai and Krylyuk, Sergiy and Davydov, Albert V. and Guo, Qianying and Lupini, Andrew R.},
abstractNote = {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.},
doi = {10.1038/s41524-021-00642-1},
journal = {npj Computational Materials},
number = 1,
volume = 7,
place = {United Kingdom},
year = {2021},
month = {11}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1038/s41524-021-00642-1
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Automatic detection of crystallographic defects in STEM images by unsupervised learning with translational invariance
journal, July 2021

In-situ formation and evolution of atomic defects in monolayer WSe 2 under electron irradiation
journal, September 2020

Super-compression of large electron microscopy time series by deep compressive sensing learning
journal, July 2021

Mapping mesoscopic phase evolution during E-beam induced transformations via deep learning of atomically resolved images
journal, June 2018

  • Vasudevan, Rama K.; Laanait, Nouamane; Ferragut, Erik M.
  • npj Computational Materials, Vol. 4, Issue 1
  • DOI: 10.1038/s41524-018-0086-7

Are Dislocations Present in Nanoparticles?: Fourier Filtering of Images Obtained From In-Situ TEM Nanoindentation
journal, July 2009

In Situ TEM Study of Catalytic Nanoparticle Reactions in Atmospheric Pressure Gas Environment
journal, September 2013

  • Xin, Huolin L.; Niu, Kaiyang; Alsem, Daan Hein
  • Microscopy and Microanalysis, Vol. 19, Issue 6
  • DOI: 10.1017/S1431927613013433

In situ atomistic insight into the growth mechanisms of single layer 2D transition metal carbides
journal, June 2018

Direct evidence for atomic defects in graphene layers
journal, August 2004

  • Hashimoto, Ayako; Suenaga, Kazu; Gloter, Alexandre
  • Nature, Vol. 430, Issue 7002
  • DOI: 10.1038/nature02817

Support Vector Data Description
journal, January 2004

The crystal structure of baddeleyite (monoclinic ZrO2)
journal, July 1959

Detection of defects in atomic-resolution images of materials using cycle analysis
journal, March 2020

  • Ovchinnikov, Oleg S.; O’Hara, Andrew; Jesse, Stephen
  • Advanced Structural and Chemical Imaging, Vol. 6, Issue 1
  • DOI: 10.1186/s40679-020-00070-x

Estimating the Support of a High-Dimensional Distribution
journal, July 2001

Deep learning analysis of defect and phase evolution during electron beam-induced transformations in WS2
journal, February 2019

A performance evaluation of local descriptors
journal, October 2005

  • Mikolajczyk, K.; Schmid, C.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, Issue 10
  • DOI: 10.1109/TPAMI.2005.188

A joint deep learning model to recover information and reduce artifacts in missing-wedge sinograms for electron tomography and beyond
journal, September 2019

Manipulating low-dimensional materials down to the level of single atoms with electron irradiation
journal, September 2017

Fire up the atom forge
journal, November 2016

  • Kalinin, Sergei V.; Borisevich, Albina; Jesse, Stephen
  • Nature, Vol. 539, Issue 7630
  • DOI: 10.1038/539485a

Automated defect analysis in electron microscopic images
journal, July 2018

A Fourier Series Method for the Determination of the Components of Interatomic Distances in Crystals
journal, September 1934

Investigating phase transitions from local crystallographic analysis based on statistical learning of atomic environments in 2D MoS 2 -ReS 2
journal, March 2021

  • Vasudevan, Rama K.; Ziatdinov, Maxim; Sharma, Vinit
  • Applied Physics Reviews, Vol. 8, Issue 1
  • DOI: 10.1063/5.0012761

LIBSVM: A library for support vector machines
journal, April 2011

  • Chang, Chih-Chung; Lin, Chih-Jen
  • ACM Transactions on Intelligent Systems and Technology, Vol. 2, Issue 3
  • DOI: 10.1145/1961189.1961199

Efficient Unsupervised Parameter Estimation for One-Class Support Vector Machines
journal, October 2018

  • Ghafoori, Zahra; Erfani, Sarah M.; Rajasegarar, Sutharshan
  • IEEE Transactions on Neural Networks and Learning Systems, Vol. 29, Issue 10
  • DOI: 10.1109/TNNLS.2017.2785792

Quantitative measurement of displacement and strain fields from HREM micrographs
journal, August 1998

Visualization and quantification of transition metal atomic mixing in Mo1−xWxS2 single layers
journal, January 2013

  • Dumcenco, Dumitru O.; Kobayashi, Haruka; Liu, Zheng
  • Nature Communications, Vol. 4, Article No. 1351
  • DOI: 10.1038/ncomms2351

0.7 Å Resolution Electron Tomography Enabled by Deep‐Learning‐Aided Information Recovery
journal, September 2020

  • Wang, Chunyang; Ding, Guanglei; Liu, Yitong
  • Advanced Intelligent Systems, Vol. 2, Issue 12
  • DOI: 10.1002/aisy.202000152

Band Gap Engineering and Layer-by-Layer Mapping of Selenium-Doped Molybdenum Disulfide
journal, December 2013

  • Gong, Yongji; Liu, Zheng; Lupini, Andrew R.
  • Nano Letters, Vol. 14, Issue 2
  • DOI: 10.1021/nl4032296

Dynamic scan control in STEM: spiral scans
journal, June 2016

  • Sang, Xiahan; Lupini, Andrew R.; Unocic, Raymond R.
  • Advanced Structural and Chemical Imaging, Vol. 2, Issue 1
  • DOI: 10.1186/s40679-016-0020-3
    Sort by:
    [ × clear filter / sort ]

    Similar Records in DOE PAGES and OSTI.GOV collections: