skip to main content

DOE PAGESDOE PAGES

This content will become publicly available on December 7, 2018

Title: Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations

Recent advances in scanning transmission electron and scanning probe microscopies have opened unprecedented opportunities in probing the materials structural parameters and various functional properties in real space with an angstrom-level precision. This progress has been accompanied by exponential increase in the size and quality of datasets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large datasets, for which a priori information on the structures of various atomic configurations and lattice defects is limited or absent. Here we demonstrate an application of deep neural networks to extracting information from atomically resolved images including location of the atomic species and type of defects. We develop a “weakly-supervised” approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set. We further apply our approach to interpret complex atomic and defect transformation, including switching between different coordination of silicon dopants in graphene as a function of time, formation of peculiar silicon dimer with mixed 3-fold and 4-fold coordination, and the motion of molecular “rotor”. In conclusion,more » this deep learning based approach resembles logic of a human operator, but can be scaled leading to significant shift in the way of extracting and analyzing information from raw experimental data.« less
Authors:
ORCiD logo [1] ; ORCiD logo [1] ; ORCiD logo [2] ; ORCiD logo [3] ; ORCiD logo [3] ; ORCiD logo [3] ; ORCiD logo [3] ; ORCiD logo [1] ; ORCiD logo [1] ; ORCiD logo [1]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Science (CNMS) and Inst. for Functional Imaging of Materials
  2. Univ. of Tennessee, Knoxville, TN (United States). Bredesen Center for Interdisciplinary Research and Graduate Education; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Science (CNMS) and Inst. for Functional Imaging of Materials
  3. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Science (CNMS)
Publication Date:
Grant/Contract Number:
AC05-00OR22725
Type:
Accepted Manuscript
Journal Name:
ACS Nano
Additional Journal Information:
Journal Volume: 11; Journal Issue: 12; Journal ID: ISSN 1936-0851
Publisher:
American Chemical Society (ACS)
Research Org:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22). Materials Sciences & Engineering Division
Country of Publication:
United States
Language:
English
Subject:
77 NANOSCIENCE AND NANOTECHNOLOGY; 36 MATERIALS SCIENCE; graphene; neural networks; scanning transmission electron microscopy (STEM); transition-metal dichalcogenide (TMDC); weakly supervised learning
OSTI Identifier:
1427646

Ziatdinov, Maxim, Dyck, Ondrej, Maksov, Artem, Li, Xufan, Sang, Xiahan, Xiao, Kai, Unocic, Raymond R., Vasudevan, Rama, Jesse, Stephen, and Kalinin, Sergei V.. Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations. United States: N. p., Web. doi:10.1021/acsnano.7b07504.
Ziatdinov, Maxim, Dyck, Ondrej, Maksov, Artem, Li, Xufan, Sang, Xiahan, Xiao, Kai, Unocic, Raymond R., Vasudevan, Rama, Jesse, Stephen, & Kalinin, Sergei V.. Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations. United States. doi:10.1021/acsnano.7b07504.
Ziatdinov, Maxim, Dyck, Ondrej, Maksov, Artem, Li, Xufan, Sang, Xiahan, Xiao, Kai, Unocic, Raymond R., Vasudevan, Rama, Jesse, Stephen, and Kalinin, Sergei V.. 2017. "Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations". United States. doi:10.1021/acsnano.7b07504.
@article{osti_1427646,
title = {Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations},
author = {Ziatdinov, Maxim and Dyck, Ondrej and Maksov, Artem and Li, Xufan and Sang, Xiahan and Xiao, Kai and Unocic, Raymond R. and Vasudevan, Rama and Jesse, Stephen and Kalinin, Sergei V.},
abstractNote = {Recent advances in scanning transmission electron and scanning probe microscopies have opened unprecedented opportunities in probing the materials structural parameters and various functional properties in real space with an angstrom-level precision. This progress has been accompanied by exponential increase in the size and quality of datasets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large datasets, for which a priori information on the structures of various atomic configurations and lattice defects is limited or absent. Here we demonstrate an application of deep neural networks to extracting information from atomically resolved images including location of the atomic species and type of defects. We develop a “weakly-supervised” approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set. We further apply our approach to interpret complex atomic and defect transformation, including switching between different coordination of silicon dopants in graphene as a function of time, formation of peculiar silicon dimer with mixed 3-fold and 4-fold coordination, and the motion of molecular “rotor”. In conclusion, this deep learning based approach resembles logic of a human operator, but can be scaled leading to significant shift in the way of extracting and analyzing information from raw experimental data.},
doi = {10.1021/acsnano.7b07504},
journal = {ACS Nano},
number = 12,
volume = 11,
place = {United States},
year = {2017},
month = {12}
}