DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Abstract

Abstract Understanding the structure of materials is crucial for engineering devices and materials with enhanced performance. Four-dimensional scanning transmission electron microscopy (4D-STEM) is capable of mapping nanometer-scale local crystallographic structure over micron-scale field of views. However, 4D-STEM datasets can contain tens of thousands of images from a wide variety of material structures, making it difficult to automate detection and classification of structures. Traditional automated analysis pipelines for 4D-STEM focus on supervised approaches, which require prior knowledge of the material structure and cannot describe anomalous or deviant structures. In this article, a pipeline for engineering 4D-STEM feature representations for unsupervised clustering using non-negative matrix factorization (NMF) is introduced. Each feature is evaluated using NMF and results are presented for both simulated and experimental data. It is shown that some data representations more reliably identify overlapping grains. Additionally, real space refinement is applied to identify spatially distinct sample regions, allowing for size and shape analysis to be performed. This work lays the foundation for improved analysis of nanoscale structural features in materials that deviate from expected crystallographic arrangement using 4D-STEM.

Authors:
ORCiD logo; ;
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1914356
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Published Article
Journal Name:
Microscopy and Microanalysis
Additional Journal Information:
Journal Name: Microscopy and Microanalysis Journal Volume: 28 Journal Issue: 6; Journal ID: ISSN 1431-9276
Publisher:
Oxford University Press
Country of Publication:
United States
Language:
English

Citation Formats

Bruefach, Alexandra, Ophus, Colin, and Scott, Mary C. Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning. United States: N. p., 2022. Web. doi:10.1017/S1431927622012259.
Bruefach, Alexandra, Ophus, Colin, & Scott, Mary C. Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning. United States. https://doi.org/10.1017/S1431927622012259
Bruefach, Alexandra, Ophus, Colin, and Scott, Mary C. Thu . "Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning". United States. https://doi.org/10.1017/S1431927622012259.
@article{osti_1914356,
title = {Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning},
author = {Bruefach, Alexandra and Ophus, Colin and Scott, Mary C.},
abstractNote = {Abstract Understanding the structure of materials is crucial for engineering devices and materials with enhanced performance. Four-dimensional scanning transmission electron microscopy (4D-STEM) is capable of mapping nanometer-scale local crystallographic structure over micron-scale field of views. However, 4D-STEM datasets can contain tens of thousands of images from a wide variety of material structures, making it difficult to automate detection and classification of structures. Traditional automated analysis pipelines for 4D-STEM focus on supervised approaches, which require prior knowledge of the material structure and cannot describe anomalous or deviant structures. In this article, a pipeline for engineering 4D-STEM feature representations for unsupervised clustering using non-negative matrix factorization (NMF) is introduced. Each feature is evaluated using NMF and results are presented for both simulated and experimental data. It is shown that some data representations more reliably identify overlapping grains. Additionally, real space refinement is applied to identify spatially distinct sample regions, allowing for size and shape analysis to be performed. This work lays the foundation for improved analysis of nanoscale structural features in materials that deviate from expected crystallographic arrangement using 4D-STEM.},
doi = {10.1017/S1431927622012259},
journal = {Microscopy and Microanalysis},
number = 6,
volume = 28,
place = {United States},
year = {Thu Dec 01 00:00:00 EST 2022},
month = {Thu Dec 01 00:00:00 EST 2022}
}

Works referenced in this record:

Strain mapping of semiconductor specimens with nm-scale resolution in a transmission electron microscope
journal, January 2016


Lattice Strain Measurement of Core@Shell Electrocatalysts with 4D Scanning Transmission Electron Microscopy Nanobeam Electron Diffraction
journal, April 2020

  • Mukherjee, Debangshu; Gamler, Jocelyn T. L.; Skrabalak, Sara E.
  • ACS Catalysis, Vol. 10, Issue 10
  • DOI: 10.1021/acscatal.0c00224

Advances in the electron diffraction characterization of atomic clusters and nanoparticles
journal, January 2021

  • Ponce, Arturo; Aguilar, Jeffery A.; Tate, Jess
  • Nanoscale Advances, Vol. 3, Issue 2
  • DOI: 10.1039/D0NA00590H

Structure Determination of Superatom Metallic Clusters Using Rapid Scanning Electron Diffraction
journal, January 2016

  • Bruma, Alina; Santiago, Ulises; Alducin, Diego
  • The Journal of Physical Chemistry C, Vol. 120, Issue 3
  • DOI: 10.1021/acs.jpcc.5b09524

Strain Mapping of Two-Dimensional Heterostructures with Subpicometer Precision
journal, May 2018


Accurate measurement of strain at interfaces in 4D-STEM: A comparison of various methods
journal, February 2021


Automated Crystal Orientation Mapping in py4DSTEM using Sparse Correlation Matching
journal, February 2022


Correlative image learning of chemo-mechanics in phase-transforming solids
journal, February 2022


Unravelling stacking order in epitaxial bilayer MX 2 using 4D-STEM with unsupervised learning
journal, August 2020


In Situ Transmission Electron Microscopy: Signal processing challenges and examples
journal, January 2022

  • Kacher, Josh; Xie, Yao; Voigt, Sven P.
  • IEEE Signal Processing Magazine, Vol. 39, Issue 1
  • DOI: 10.1109/MSP.2021.3119284

Variable Coherence Microscopy: a Rich Source of Structural Information from Disordered Materials
journal, March 1996

  • Treacy, M. M. J.; Gibson, J. M.
  • Acta Crystallographica Section A Foundations of Crystallography, Vol. 52, Issue 2
  • DOI: 10.1107/S0108767395012876

Image Matching from Handcrafted to Deep Features: A Survey
journal, August 2020

  • Ma, Jiayi; Jiang, Xingyu; Fan, Aoxiang
  • International Journal of Computer Vision, Vol. 129, Issue 1
  • DOI: 10.1007/s11263-020-01359-2

Improvements in electron diffraction pattern automatic indexing algorithms
journal, October 2017

  • Meng, Yifei; Zuo, Jian-Min
  • The European Physical Journal Applied Physics, Vol. 80, Issue 1
  • DOI: 10.1051/epjap/2017160444

Intrinsic helical twist and chirality in ultrathin tellurium nanowires
journal, January 2021

  • Londoño-Calderon, Alejandra; Williams, Darrick J.; Schneider, Matthew M.
  • Nanoscale, Vol. 13, Issue 21
  • DOI: 10.1039/D1NR01442K

Polyol Synthesis of Ultrathin Pd Nanowires via Attachment-Based Growth and Their Enhanced Activity towards Formic Acid Oxidation
journal, August 2013

  • Wang, Yi; Choi, Sang-Il; Zhao, Xin
  • Advanced Functional Materials, Vol. 24, Issue 1
  • DOI: 10.1002/adfm.201302339

Patterned probes for high precision 4D-STEM bragg measurements
journal, February 2020


Machine Learning Assisted Pattern Matching: Insight into Oxide Electronic Device Performance by Phase Determination in 4D-STEM Datasets
journal, July 2020

  • Zintler, Alexander; Eilhardt, Robert; Wang, Shuai
  • Microscopy and Microanalysis, Vol. 26, Issue S2
  • DOI: 10.1017/S1431927620019790

The scattering of electrons by atoms and crystals. I. A new theoretical approach
journal, October 1957


Learning the parts of objects by non-negative matrix factorization
journal, October 1999

  • Lee, Daniel D.; Seung, H. Sebastian
  • Nature, Vol. 401, Issue 6755
  • DOI: 10.1038/44565

Rapid and Semi-Automated Analysis of 4D-STEM data via Unsupervised Learning
journal, July 2021


Automated nanocrystal orientation and phase mapping in the transmission electron microscope on the basis of precession electron diffraction
journal, January 2010

  • Rauch, Edgar F.; Portillo, Joaquin; Nicolopoulos, Stavros
  • Zeitschrift für Kristallographie, Vol. 225, Issue 2-3
  • DOI: 10.1524/zkri.2010.1205

py4DSTEM: A Software Package for Four-Dimensional Scanning Transmission Electron Microscopy Data Analysis
journal, May 2021


Orientation mapping of semicrystalline polymers using scanning electron nanobeam diffraction
journal, September 2016


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

  • van der Walt, Stéfan; Schönberger, Johannes L.; Nunez-Iglesias, Juan
  • PeerJ, Vol. 2
  • DOI: 10.7717/peerj.453

Advanced Computing in Electron Microscopy
book, January 2020


Mechanistic Insights into Superlattice Transformation at a Single Nanocrystal Level Using Nanobeam Electron Diffraction
journal, June 2020


Direct measurement of nanostructural change during in situ deformation of a bulk metallic glass
journal, June 2019


Insights into Initial Kinetic Nucleation of Gold Nanocrystals
journal, June 2010

  • Yao, Tao; Sun, Zhihu; Li, Yuanyuan
  • Journal of the American Chemical Society, Vol. 132, Issue 22
  • DOI: 10.1021/ja101101d

Unsupervised Data Mining in nanoscale X-ray Spectro-Microscopic Study of NdFeB Magnet
journal, September 2016

  • Duan, Xiaoyue; Yang, Feifei; Antono, Erin
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep34406

Real-Time Interactive 4D-STEM Phase-Contrast Imaging From Electron Event Representation Data: Less computation with the right representation
journal, January 2022

  • Pelz, Philipp M.; Johnson, Ian; Ophus, Colin
  • IEEE Signal Processing Magazine, Vol. 39, Issue 1
  • DOI: 10.1109/MSP.2021.3120981

Feret‘s Statistical Diameter as a Measure of Particle Size
journal, August 1948


Optimizing disk registration algorithms for nanobeam electron diffraction strain mapping
journal, May 2017


Diffraction imaging of nanocrystalline structures in organic semiconductor molecular thin films
journal, June 2019


Methods for orientation and phase identification of nano-sized embedded secondary phase particles by 4D scanning precession electron diffraction
journal, August 2019

  • Rauch, E. F.; Véron, M.
  • Acta Crystallographica Section B Structural Science, Crystal Engineering and Materials, Vol. 75, Issue 4
  • DOI: 10.1107/S2052520619007583

Machine Learning Pipeline for Segmentation and Defect Identification from High-Resolution Transmission Electron Microscopy Data
journal, May 2021

  • Groschner, Catherine K.; Choi, Christina; Scott, Mary C.
  • Microscopy and Microanalysis, Vol. 27, Issue 3
  • DOI: 10.1017/S1431927621000386

Multivariate Analysis Applications in X-ray Diffraction
journal, December 2020

  • Guccione, Pietro; Lopresti, Mattia; Milanesio, Marco
  • Crystals, Vol. 11, Issue 1
  • DOI: 10.3390/cryst11010012

A fast image simulation algorithm for scanning transmission electron microscopy
journal, May 2017


Experimental Evidence of Icosahedral and Decahedral Packing in One-Dimensional Nanostructures
journal, August 2011

  • Velázquez-Salazar, J. Jesús; Esparza, Rodrigo; Mejía-Rosales, Sergio Javier
  • ACS Nano, Vol. 5, Issue 8
  • DOI: 10.1021/nn202495r

Nanoscale characterization of crystalline and amorphous phases in silicon oxycarbide ceramics using 4D-STEM
journal, November 2021


Measurement of effective source distribution and its importance for quantitative interpretation of STEM images
journal, July 2010


Chiral Transformation: From Single Nanowire to Double Helix
journal, November 2011

  • Wang, Yong; Wang, Qingxiao; Sun, Hang
  • Journal of the American Chemical Society, Vol. 133, Issue 50
  • DOI: 10.1021/ja208121c

Non-negative matrix factorization for mining big data obtained using four-dimensional scanning transmission electron microscopy
journal, February 2021


Diffraction contrast imaging using virtual apertures
journal, August 2015


Unsupervised machine learning applied to scanning precession electron diffraction data
journal, March 2019

  • Martineau, Ben H.; Johnstone, Duncan N.; van Helvoort, Antonius T. J.
  • Advanced Structural and Chemical Imaging, Vol. 5, Issue 1
  • DOI: 10.1186/s40679-019-0063-3

Insights into Texture and Phase Coexistence in Polycrystalline and Polyphasic Ferroelectric HfO2 Thin Films using 4D-STEM
journal, August 2018

  • Grimley, Everett D.; Frisone, Sam; Schenk, Tony
  • Microscopy and Microanalysis, Vol. 24, Issue S1
  • DOI: 10.1017/S1431927618001411

A Critical Size for Emergence of Nonbulk Electronic and Geometric Structures in Dodecanethiolate-Protected Au Clusters
journal, January 2015

  • Negishi, Yuichi; Nakazaki, Tafu; Malola, Sami
  • Journal of the American Chemical Society, Vol. 137, Issue 3
  • DOI: 10.1021/ja5109968