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

Title: Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data

Abstract

In this paper, we present a novel methodology based on machine learning to extract lattice variations in crystalline materials, at the nanoscale, from an x-ray Bragg diffraction-based imaging technique. By employing a full-field microscopy setup, we capture real space images of materials, with imaging contrast determined solely by the x-ray diffracted signal. The data sets that emanate from this imaging technique are a hybrid of real space information (image spatial support) and reciprocal lattice space information (image contrast), and are intrinsically multidimensional (5D). By a judicious application of established unsupervised machine learning techniques and multivariate analysis to this multidimensional data cube, we show how to extract features that can be ascribed physical interpretations in terms of common structural distortions, such as lattice tilts and dislocation arrays. Finally, we demonstrate this 'big data' approach to x-ray diffraction microscopy by identifying structural defects present in an epitaxial ferroelectric thin-film of lead zirconate titanate.

Authors:
ORCiD logo [1];  [2];  [3]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences; Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Inst. for Functional Imaging of Materials
  2. Argonne National Lab. (ANL), Argonne, IL (United States). X-ray Science Division
  3. Paul Scherrer Inst. (PSI), Villigen (Switzerland). Swiss Light Source
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
Contributing Org.:
Argonne National Lab. (ANL), Argonne, IL (United States); Paul Scherrer Inst. (PSI), Villigen (Switzerland)
OSTI Identifier:
1302903
Alternate Identifier(s):
OSTI ID: 1287749
Grant/Contract Number:  
AC05-00OR22725; AC02-06CH11357
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Nanotechnology
Additional Journal Information:
Journal Volume: 27; Journal Issue: 37; Journal ID: ISSN 0957-4484
Publisher:
IOP Publishing
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; 47 OTHER INSTRUMENTATION; x-ray diffraction imaging; computer vision; machine learning; multivariate analysis; ferroelectric materials; epitaxial thin-film

Citation Formats

Laanait, Nouamane, Zhang, Zhan, and Schlepütz, Christian M. Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data. United States: N. p., 2016. Web. doi:10.1088/0957-4484/27/37/374002.
Laanait, Nouamane, Zhang, Zhan, & Schlepütz, Christian M. Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data. United States. doi:10.1088/0957-4484/27/37/374002.
Laanait, Nouamane, Zhang, Zhan, and Schlepütz, Christian M. Tue . "Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data". United States. doi:10.1088/0957-4484/27/37/374002. https://www.osti.gov/servlets/purl/1302903.
@article{osti_1302903,
title = {Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data},
author = {Laanait, Nouamane and Zhang, Zhan and Schlepütz, Christian M.},
abstractNote = {In this paper, we present a novel methodology based on machine learning to extract lattice variations in crystalline materials, at the nanoscale, from an x-ray Bragg diffraction-based imaging technique. By employing a full-field microscopy setup, we capture real space images of materials, with imaging contrast determined solely by the x-ray diffracted signal. The data sets that emanate from this imaging technique are a hybrid of real space information (image spatial support) and reciprocal lattice space information (image contrast), and are intrinsically multidimensional (5D). By a judicious application of established unsupervised machine learning techniques and multivariate analysis to this multidimensional data cube, we show how to extract features that can be ascribed physical interpretations in terms of common structural distortions, such as lattice tilts and dislocation arrays. Finally, we demonstrate this 'big data' approach to x-ray diffraction microscopy by identifying structural defects present in an epitaxial ferroelectric thin-film of lead zirconate titanate.},
doi = {10.1088/0957-4484/27/37/374002},
journal = {Nanotechnology},
number = 37,
volume = 27,
place = {United States},
year = {Tue Aug 09 00:00:00 EDT 2016},
month = {Tue Aug 09 00:00:00 EDT 2016}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: