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

Guo, Yueming; Kalinin, Sergei V.; Cai, Hui; Xiao, Kai; Krylyuk, Sergiy; Davydov, Albert V.; Guo, Qianying; Lupini, Andrew R.

doi:10.1038/s41524-021-00642-1

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

Journal Article · 08 November 2021 · npj Computational Materials

DOI: https://doi.org/10.1038/s41524-021-00642-1 · OSTI ID:1829523

Guo, Yueming;

; Cai, Hui;

; Krylyuk, Sergiy;

; Guo, Qianying;

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.

View Journal Article

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1829523

Journal Information:: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 7; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (31)

0.7 Å Resolution Electron Tomography Enabled by Deep‐Learning‐Aided Information Recovery Wang, Chunyang; Ding, Guanglei; Liu, Yitong Advanced Intelligent Systems, Vol. 2, Issue 12 https://doi.org/10.1002/aisy.202000152	journal	September 2020
Quantitative measurement of displacement and strain fields from HREM micrographs Hÿtch, M. J.; Snoeck, E.; Kilaas, R. Ultramicroscopy, Vol. 74, Issue 3, p. 131-146 https://doi.org/10.1016/S0304-3991(98)00035-7	journal	August 1998
Super-compression of large electron microscopy time series by deep compressive sensing learning Zheng, Siming; Wang, Chunyang; Yuan, Xin Patterns, Vol. 2, Issue 7 https://doi.org/10.1016/j.patter.2021.100292	journal	July 2021
Manipulating low-dimensional materials down to the level of single atoms with electron irradiation Susi, Toma; Meyer, Jannik C.; Kotakoski, Jani Ultramicroscopy, Vol. 180 https://doi.org/10.1016/j.ultramic.2017.03.005	journal	September 2017
Are Dislocations Present in Nanoparticles?: Fourier Filtering of Images Obtained From In-Situ TEM Nanoindentation Carlton, C.; Ferreira, Pj Microscopy and Microanalysis, Vol. 15, Issue S2 https://doi.org/10.1017/S1431927609096585	journal	July 2009
In Situ TEM Study of Catalytic Nanoparticle Reactions in Atmospheric Pressure Gas Environment Xin, Huolin L.; Niu, Kaiyang; Alsem, Daan Hein Microscopy and Microanalysis, Vol. 19, Issue 6 https://doi.org/10.1017/S1431927613013433	journal	September 2013
Automatic detection of crystallographic defects in STEM images by unsupervised learning with translational invariance Guo, Yueming; Lupini, Andrew R.; Cai, Hui Microscopy and Microanalysis, Vol. 27, Issue S1 https://doi.org/10.1017/S1431927621005407	journal	July 2021
Deep Learning Enabled Strain Mapping of Single-Atom Defects in Two-Dimensional Transition Metal Dichalcogenides with Sub-Picometer Precision Lee, Chia-Hao; Khan, Abid; Luo, Di Nano Letters, Vol. 20, Issue 5 https://doi.org/10.1021/acs.nanolett.0c00269	journal	April 2020
Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations Ziatdinov, Maxim; Dyck, Ondrej; Maksov, Artem ACS Nano, Vol. 11, Issue 12 https://doi.org/10.1021/acsnano.7b07504	journal	October 2016
Band Gap Engineering and Layer-by-Layer Mapping of Selenium-Doped Molybdenum Disulfide Gong, Yongji; Liu, Zheng; Lupini, Andrew R. Nano Letters, Vol. 14, Issue 2 https://doi.org/10.1021/nl4032296	journal	December 2013
Support Vector Data Description Tax, David M. J.; Duin, Robert P. W. Machine Learning, Vol. 54, Issue 1 https://doi.org/10.1023/B:MACH.0000008084.60811.49	journal	January 2004
Fire up the atom forge Kalinin, Sergei V.; Borisevich, Albina; Jesse, Stephen Nature, Vol. 539, Issue 7630 https://doi.org/10.1038/539485a	journal	November 2016
Direct evidence for atomic defects in graphene layers Hashimoto, Ayako; Suenaga, Kazu; Gloter, Alexandre Nature, Vol. 430, Issue 7002 https://doi.org/10.1038/nature02817	journal	August 2004
Visualization and quantification of transition metal atomic mixing in Mo_1−xW_xS₂ single layers Dumcenco, Dumitru O.; Kobayashi, Haruka; Liu, Zheng Nature Communications, Vol. 4, Article No. 1351 https://doi.org/10.1038/ncomms2351	journal	January 2013
In situ atomistic insight into the growth mechanisms of single layer 2D transition metal carbides Sang, Xiahan; Xie, Yu; Yilmaz, Dundar E. Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-04610-0	journal	June 2018
Mapping mesoscopic phase evolution during E-beam induced transformations via deep learning of atomically resolved images Vasudevan, Rama K.; Laanait, Nouamane; Ferragut, Erik M. npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0086-7	journal	June 2018
Automated defect analysis in electron microscopic images Li, Wei; Field, Kevin G.; Morgan, Dane npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0093-8	journal	July 2018
Deep learning analysis of defect and phase evolution during electron beam-induced transformations in WS2 Maksov, Artem; Dyck, Ondrej; Wang, Kai npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0152-9	journal	February 2019
A joint deep learning model to recover information and reduce artifacts in missing-wedge sinograms for electron tomography and beyond Ding, Guanglei; Liu, Yitong; Zhang, Rui Scientific Reports, Vol. 9, Issue 1 https://doi.org/10.1038/s41598-019-49267-x	journal	September 2019
TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images Lin, Ruoqian; Zhang, Rui; Wang, Chunyang Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-84499-w	journal	March 2021
Investigating phase transitions from local crystallographic analysis based on statistical learning of atomic environments in 2D MoS ₂ -ReS ₂ Vasudevan, Rama K.; Ziatdinov, Maxim; Sharma, Vinit Applied Physics Reviews, Vol. 8, Issue 1 https://doi.org/10.1063/5.0012761	journal	March 2021
In-situ formation and evolution of atomic defects in monolayer WSe ₂ under electron irradiation Leiter, Robert; Li, Yueliang; Kaiser, Ute Nanotechnology, Vol. 31, Issue 49 https://doi.org/10.1088/1361-6528/abb335	journal	September 2020
A Fourier Series Method for the Determination of the Components of Interatomic Distances in Crystals Patterson, A. L. Physical Review, Vol. 46, Issue 5 https://doi.org/10.1103/PhysRev.46.372	journal	September 1934
Silicon–Carbon Bond Inversions Driven by 60-keV Electrons in Graphene Susi, Toma; Kotakoski, Jani; Kepaptsoglou, Demie Physical Review Letters, Vol. 113, Issue 11 https://doi.org/10.1103/PhysRevLett.113.115501	journal	September 2014
The crystal structure of baddeleyite (monoclinic ZrO2) McCullough, J. D.; Trueblood, K. N. Acta Crystallographica, Vol. 12, Issue 7 https://doi.org/10.1107/S0365110X59001530	journal	July 1959
Efficient Unsupervised Parameter Estimation for One-Class Support Vector Machines Ghafoori, Zahra; Erfani, Sarah M.; Rajasegarar, Sutharshan IEEE Transactions on Neural Networks and Learning Systems, Vol. 29, Issue 10 https://doi.org/10.1109/TNNLS.2017.2785792	journal	October 2018
A performance evaluation of local descriptors Mikolajczyk, K.; Schmid, C. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, Issue 10 https://doi.org/10.1109/TPAMI.2005.188	journal	October 2005
LIBSVM: A library for support vector machines Chang, Chih-Chung; Lin, Chih-Jen ACM Transactions on Intelligent Systems and Technology, Vol. 2, Issue 3 https://doi.org/10.1145/1961189.1961199	journal	April 2011
Estimating the Support of a High-Dimensional Distribution Schölkopf, Bernhard; Platt, John C.; Shawe-Taylor, John Neural Computation, Vol. 13, Issue 7 https://doi.org/10.1162/089976601750264965	journal	July 2001
Dynamic scan control in STEM: spiral scans Sang, Xiahan; Lupini, Andrew R.; Unocic, Raymond R. Advanced Structural and Chemical Imaging, Vol. 2, Issue 1 https://doi.org/10.1186/s40679-016-0020-3	journal	June 2016
Detection of defects in atomic-resolution images of materials using cycle analysis Ovchinnikov, Oleg S.; O’Hara, Andrew; Jesse, Stephen Advanced Structural and Chemical Imaging, Vol. 6, Issue 1 https://doi.org/10.1186/s40679-020-00070-x	journal	March 2020

Similar Records

Galaxy morphological classification in deep-wide surveys via unsupervised machine learning

Journal Article · 2019 · Monthly Notices of the Royal Astronomical Society · OSTI ID:1575933

Martin, G.; Kaviraj, S.; Hocking, A.; +2 more

Self-Taught Anomaly Detection With Hybrid Unsupervised/Supervised Machine Learning in Optical Networks

Journal Article · 2019 · Journal of Lightwave Technology · OSTI ID:1612677

Chen, Xiaoliang; Li, Baojia; Proietti, Roberto; +2 more

Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning

Journal Article · 2022 · Microscopy and Microanalysis · OSTI ID:1914356

Bruefach, Alexandra; Ophus, Colin; Scott, Mary C.

Related Subjects

36 MATERIALS SCIENCE

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

Citation Formats

References (31)

Similar Records

Related Subjects