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

T P McAuliffe; D Dye; T B Britton

doi:10.1016/j.ultramic.2020.113132

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

Ultramicroscopy. 2020 Dec:219:113132. doi: 10.1016/j.ultramic.2020.113132. Epub 2020 Oct 8.

Authors

T P McAuliffe¹, D Dye², T B Britton²

Affiliations

¹ Department of Materials, Imperial College London, Prince Consort Road, London, UK. Electronic address: t.mcauliffe17@imperial.ac.uk.
² Department of Materials, Imperial College London, Prince Consort Road, London, UK.

PMID: 33053461
DOI: 10.1016/j.ultramic.2020.113132

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 principal component analysis, non-negative matrix factorisation, 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.

Keywords: EBSD; Machine Learning; Microstructure; Superalloy; Virtual imaging.