Spherical-angular dark field imaging and sensitive microstructural phase clustering with unsupervised machine learning

Abstract

Electron backscatter diffraction is a widely used technique for nano- to micro-scale analysis of crystal structure and orientation. Backscatter patterns produced by an alloy solid solution matrix and its ordered superlattice exhibit only extremely subtle differences, due to the inelastic scattering that precedes coherent diffraction. We show that unsupervised machine learning (with PCA, NMF, and an autoencoder neural network) is well suited to fine feature extraction and superlattice/matrix classification. Remapping cluster average patterns onto the diffraction sphere lets us compare Kikuchi band profiles to dynamical simulations, confirm the superlattice stoichiometry, and facilitate virtual imaging with a spherical solid angle aperture. This pipeline now enables unparalleled mapping of exquisite crystallographic detail from a wide range of materials within the scanning electron microscope.

arXiv commentUpdated with corrections from peer review

References in corpus (3)

• Paradigm shift in electron-based crystallography via machine learning
• Applications of Multivariate Statistical Methods and Simulation Libraries to Analysis of Electron Backscatter Diffraction and Transmission Kikuchi Diffraction Datasets
• Advancing characterisation with statistics from correlative electron diffraction and X-ray spectroscopy, in the scanning electron microscope

Cited by in corpus (4)

• Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Features
• Comparison of Kikuchi Diffraction Geometries in Scanning Electron Microscope
• Orientation-Adaptive Virtual Imaging of Defects using EBSD
• Characterization of WSe${}_2$ films using reflection Kikuchi diffraction in the scanning electron microscope and multivariate statistical analyses