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

TL;DR

This paper introduces a novel unsupervised machine learning pipeline that enhances the analysis of electron backscatter diffraction patterns, enabling detailed microstructural phase classification and virtual imaging within SEMs.

Contribution

It presents a new approach combining PCA, NMF, and autoencoders for fine feature extraction and classification of subtle diffraction pattern differences in materials.

Findings

Effective superlattice/matrix classification achieved

Remapping patterns aids comparison with simulations

Enables detailed crystallographic mapping in SEMs

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.