Multi-modal data-driven microstructure characterization

TL;DR

This paper presents an automated, data-driven approach for microstructure characterization using multimodal analysis techniques, enabling more objective and efficient grain and phase segmentation in electron backscatter diffraction data.

Contribution

It introduces a workflow that automates hyperparameter selection and maps latent features to physical quantities, improving microstructure analysis accuracy and efficiency.

Findings

Automated hyperparameter decision-making for PCA and NMF.

Latent space features correlate with physical microstructural properties.

Optimal ROI size is approximately twice the grain size.

Abstract

Electron backscatter diffraction is one of the most prevalent techniques used for microstructural characterization. In recent years, there has been an increase in the use of data-driven methods to analyze raw Kikuchi patterns. However, most of these require user input and the interpretation of the data-derived features is often challenging and subject to \textit{informed interpretation}. By using a combination of principal component analysis, constrained non-negative matrix factorization, and a variational autoencoder along with information-theoretical considerations on a multimodal dataset, it is shown that a) automated decision on method-specific hyperparameters, here the number of components in principal component analysis, the number of components for constrained non-negative matrix factorization, and the selection of reference constraints; and b) latent space features can be mapped to physically-meaningful quantities. In addition, the recommended region-of-interest (ROI) size for optimal model performance is approximated automatically to be twice the characteristic grain size based on information content of the dataset. Implemented in a workflow, this allows for a transferable, dataset-specific autonomous data-driven phase and grain segmentation including grain boundary detection and the analysis of very-small-angle intra-grain variations to complement conventional electron backscatter analysis.