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 Laboratory (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. https://doi.org/10.1088/0957-4484/27/37/374002
Laanait, Nouamane, Zhang, Zhan, and Schlepütz, Christian M. 2016. "Imaging nanoscale lattice variations by machine learning of x-ray diffraction microscopy data". United States. https://doi.org/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},
url = {https://www.osti.gov/biblio/1302903}, journal = {Nanotechnology},
issn = {0957-4484},
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

Citation Metrics:
Cited by: 15 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: X-ray Diffraction Microscopy of epitaxial thin-films. A) Reciprocal space volume of an epitaxial thin-film of Pb(Zr0.2Ti0.8)O3 (100 nm) on SrRuO3 (50nm)/SrTiO3 (001). (B) Close-up of the PZT 002 reflection taken as an HL-cut from the reciprocal space volume in (A). Units are given in reciprocal lattice units (r.l.u)more » of the single crystal substrate, SrTiO3 (001), and a normalized intensity. (C) Schematic of the X-ray Diffraction microscope (XDM) (not drawn to scale). The scattering vector q = koutkin determines the image contrast in an XDM image shown in (B) with q PZT (002). XDM makes a direct space image out of the thin-film scattering information encoded in reciprocal space (B). Image scale bar is 2 𝜇m. The large spread in reciprocal space of the PZT 002 reflection is revealed by XDM to be caused by structural distortions in PZT due to the presence of a network of dislocation arrays and small-angle tilt grain boundaries (dark contrast lines in D) as a result of the thin-film relieving the epitaxial strain imposed by the substrate.« less

Save / Share:

Works referenced in this record:

Ubiquitous Interplay Between Charge Ordering and High-Temperature Superconductivity in Cuprates
journal, December 2013


Flexoelectric rotation of polarization in ferroelectric thin films
journal, October 2011


Inhomogeneity of charge-density-wave order and quenched disorder in a high-Tc superconductor
journal, September 2015


Three-dimensional charge density wave order in YBa2Cu3O6.67 at high magnetic fields
journal, November 2015


Strain-induced coupling of electrical polarization and structural defects in SrMnO3 films
journal, June 2015


Beyond crystallography: Diffractive imaging using coherent x-ray light sources
journal, April 2015


Chemical composition mapping with nanometre resolution by soft X-ray microscopy
journal, September 2014


Multimodality hard-x-ray imaging of a chromosome with nanoscale spatial resolution
journal, February 2016


X-ray-driven reaction front dynamics at calcite-water interfaces
journal, September 2015


Reconstructing state mixtures from diffraction measurements
journal, February 2013


X-ray micro-beam characterization of lattice rotations and distortions due to an individual dislocation
journal, November 2013


Imaging Local Polarization in Ferroelectric Thin Films by Coherent X-Ray Bragg Projection Ptychography
journal, April 2013


Full-field X-ray reflection microscopy of epitaxial thin-films
journal, October 2014


Efficient modeling of Bragg coherent x-ray nanobeam diffraction
journal, January 2015


Suppressed Dependence of Polarization on Epitaxial Strain in Highly Polar Ferroelectrics
journal, May 2007


Angle calculations for a (2+3)-type diffractometer: focus on area detectors
journal, December 2010


xrayutilities : a versatile tool for reciprocal space conversion of scattering data recorded with linear and area detectors
journal, July 2013


scikit-image: image processing in Python
journal, January 2014


Methods of Multivariate Analysis
book, July 2012


Misfit strain relaxation by dislocations in SrRuO3/SrTiO3 (001) heteroepitaxy
journal, May 2004


Deterministic control of ferroelastic switching in multiferroic materials
journal, October 2009


Anomalous expansion of the copper-apical-oxygen distance in superconducting cuprate bilayers
journal, April 2010


Methods of Multivariate Analysis.
journal, August 1996


Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps
journal, May 2021


Methods of Multivariate Analysis
journal, February 2003


Strain-induced coupling of electrical polarization and structural defects in SrMnO₃ films
text, January 2015


Methods of Multivariate Analysis
journal, September 1998


Suppressed dependence of polarization on epitaxial strain in highly polar ferroelectrics
text, January 2007


Works referencing / citing this record:

Reconstructing phase diagrams from local measurements via Gaussian processes: mapping the temperature-composition space to confidence
journal, April 2018


Characterization of domain distributions by second harmonic generation in ferroelectrics
journal, July 2018


Optical creation of a supercrystal with three-dimensional nanoscale periodicity
journal, March 2019


Competing phases in epitaxial vanadium dioxide at nanoscale
journal, August 2019


Dynamic X-ray diffraction imaging of the ferroelectric response in bismuth ferrite
journal, March 2017


Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform
journal, April 2018


Convolutional neural networks for grazing incidence x-ray scattering patterns: thin film structure identification
journal, March 2019


Estimation of Imaginary Movements Quality Based on Machine Learning for Brain Computer Interface Applications
journal, October 2018


Competing Phases in Epitaxial Vanadium Dioxide at Nanoscale
preprint, January 2019


Machine learning and big scientific data
journal, January 2020

  • Hey, Tony; Butler, Keith; Jackson, Sam
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 378, Issue 2166
  • https://doi.org/10.1098/rsta.2019.0054

Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform
journal, April 2018


Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.