On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets
Open Access
- 1 January 2025
- journal article
- Published by AIP Publishing in APL Materials
- Vol. 13 (1)
Abstract
This study considers the issue of automated segmentation of scanning transmission electron microscopy (STEM) datasets using unsupervised machine learning approaches. To this end, a systematic comparison of two clustering workflows that had been established in previous literature was performed on two distinct material systems—an experimentally acquired Co2FeSi Heusler alloy and a simulated Au-matrix and Al2Cu precipitate. The cluster outputs were evaluated using a variety of unsupervised clustering metrics measuring separation and cohesion. It was found that the cluster output of a variational autoencoder (VAE) performed better compared to a more conventional latent transformation via Uniform Manifold Approximation & Projection (UMAP) on 4D-STEM data alone. However, the UMAP workflow applied to merged 4D-STEM and STEM-energy dispersive x-ray (STEM-EDX) data produced the best cluster output overall, indicating that the correlated information provides beneficial constraints to the latent space. A potential general workflow for analyzing merged datasets to identify structural-composition changes across different material systems is proposed.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/R00661X/1, EP/S019367/1, EP/P025021/1, EP/S021531/1, EP/P025498/1, EP/Y014405/1)
- Science and Technology Facilities Council (Oxford-Diamond-STFC Studentship)
This publication has 38 references indexed in Scilit:
- 4D‐STEM Nanoscale Strain Analysis in van der Waals Materials: Advancing beyond Planar ConfigurationsSmall Science, 2024
- Scanning precession electron diffraction data analysis approaches for phase mapping of precipitates in aluminium alloysUltramicroscopy, 2023
- Correlated electron diffraction and energy-dispersive X-ray for automated microstructure analysisComputational Materials Science, 2023
- espm: A Python library for the simulation of STEM-EDXS datasetsUltramicroscopy, 2023
- Advances in Artificial Intelligence and Data Engineering2021
- Pulsed laser deposited Co2FeSi Heusler alloy thin films: Effect of different thermal growth processesJournal of Alloys and Compounds, 2019
- An extensive comparative study of cluster validity indicesPattern Recognition, 2013
- International Encyclopedia of Statistical Science2011
- Positive matrix factorization: A non‐negative factor model with optimal utilization of error estimates of data valuesEnvironmetrics, 1994
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987