skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on March 1, 2021

Title: Atomic resolution convergent beam electron diffraction analysis using convolutional neural networks

Abstract

Two types of convolutional neural network (CNN) models, a discrete classification network and a continuous regression network, were trained to determine local sample thickness from convergent beam diffraction (CBED) patterns of SrTiO 3 collected in a scanning transmission electron microscope (STEM) at atomic column resolution. Acquisition of atomic resolution CBED patterns for this purpose requires careful balancing of CBED feature size in pixels, acquisition speed, and detector dynamic range. The training datasets were derived from multislice simulations, which must be convolved with incoherent source broadening. Sample thicknesses were also determined using quantitative high-angle annular dark-field (HAADF) STEM images acquired simultaneously. The regression CNN performed well on sample thinner than 35 nm, with 70% of the CNN results within 1 nm of HAADF thickness, and 1.0 nm overall root mean square error between the two measurements. The classification CNN was trained for a thicknesses up to 100 nm and yielded 66% of CNN results within one classification increment of 2 nm of HAADF thickness. Our approach depends on methods from computer vision including transfer learning and image augmentation.

Authors:
 [1];  [1];  [1];  [1]
  1. Univ. of Wisconsin, Madison, WI (United States). Dept. of Materials Science and Engineering
Publication Date:
Research Org.:
Univ. of Wisconsin, Madison, WI (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
Contributing Org.:
[Wisconsin REU program]
OSTI Identifier:
1593819
Alternate Identifier(s):
OSTI ID: 1592812
Grant/Contract Number:  
[FG02-08ER46547]
Resource Type:
Accepted Manuscript
Journal Name:
Ultramicroscopy
Additional Journal Information:
[ Journal Volume: 210; Journal Issue: C]; Journal ID: ISSN 0304-3991
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; Convolutional neural network; Deep learning; Machine learning; Scanning transmission electron microscopy; Convergent beam electron diffraction

Citation Formats

Zhang, Chenyu, Feng, Jie, DaCosta, Luis Rangel, and Voyles, Paul. M. Atomic resolution convergent beam electron diffraction analysis using convolutional neural networks. United States: N. p., 2020. Web. doi:10.1016/j.ultramic.2019.112921.
Zhang, Chenyu, Feng, Jie, DaCosta, Luis Rangel, & Voyles, Paul. M. Atomic resolution convergent beam electron diffraction analysis using convolutional neural networks. United States. doi:10.1016/j.ultramic.2019.112921.
Zhang, Chenyu, Feng, Jie, DaCosta, Luis Rangel, and Voyles, Paul. M. Sun . "Atomic resolution convergent beam electron diffraction analysis using convolutional neural networks". United States. doi:10.1016/j.ultramic.2019.112921.
@article{osti_1593819,
title = {Atomic resolution convergent beam electron diffraction analysis using convolutional neural networks},
author = {Zhang, Chenyu and Feng, Jie and DaCosta, Luis Rangel and Voyles, Paul. M.},
abstractNote = {Two types of convolutional neural network (CNN) models, a discrete classification network and a continuous regression network, were trained to determine local sample thickness from convergent beam diffraction (CBED) patterns of SrTiO3 collected in a scanning transmission electron microscope (STEM) at atomic column resolution. Acquisition of atomic resolution CBED patterns for this purpose requires careful balancing of CBED feature size in pixels, acquisition speed, and detector dynamic range. The training datasets were derived from multislice simulations, which must be convolved with incoherent source broadening. Sample thicknesses were also determined using quantitative high-angle annular dark-field (HAADF) STEM images acquired simultaneously. The regression CNN performed well on sample thinner than 35 nm, with 70% of the CNN results within 1 nm of HAADF thickness, and 1.0 nm overall root mean square error between the two measurements. The classification CNN was trained for a thicknesses up to 100 nm and yielded 66% of CNN results within one classification increment of 2 nm of HAADF thickness. Our approach depends on methods from computer vision including transfer learning and image augmentation.},
doi = {10.1016/j.ultramic.2019.112921},
journal = {Ultramicroscopy},
number = [C],
volume = [210],
place = {United States},
year = {2020},
month = {3}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on March 1, 2021
Publisher's Version of Record

Save / Share: