On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-01-01
|
| Series: | APL Materials |
| Online Access: | http://dx.doi.org/10.1063/5.0246329 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542764669075456 |
|---|---|
| author | Zhiquan Kho Andy Bridger Keith Butler Ercin C. Duran Mohsen Danaie Alexander S. Eggeman |
| author_facet | Zhiquan Kho Andy Bridger Keith Butler Ercin C. Duran Mohsen Danaie Alexander S. Eggeman |
| author_sort | Zhiquan Kho |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-fddcd7ec58674b078c8516b247f4ccea |
| institution | Kabale University |
| issn | 2166-532X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Materials |
| spelling | doaj-art-fddcd7ec58674b078c8516b247f4ccea2025-02-03T16:42:31ZengAIP Publishing LLCAPL Materials2166-532X2025-01-01131010901010901-1310.1063/5.0246329On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasetsZhiquan Kho0Andy Bridger1Keith Butler2Ercin C. Duran3Mohsen Danaie4Alexander S. Eggeman5Department of Materials, University of Manchester, Manchester M13 9PL, United KingdomDiamond Light Source, Oxfordshire, Didcot OX11 0DE, United KingdomDepartment of Chemistry, University College London, London WC1E 6BT, United KingdomDepartment of Metallurgical and Materials Engineering, Istanbul Technical University, Istanbul, TürkiyeDiamond Light Source, Oxfordshire, Didcot OX11 0DE, United KingdomDepartment of Materials, University of Manchester, Manchester M13 9PL, United KingdomThis 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.http://dx.doi.org/10.1063/5.0246329 |
| spellingShingle | Zhiquan Kho Andy Bridger Keith Butler Ercin C. Duran Mohsen Danaie Alexander S. Eggeman On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets APL Materials |
| title | On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets |
| title_full | On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets |
| title_fullStr | On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets |
| title_full_unstemmed | On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets |
| title_short | On the use of clustering workflows for automated microstructure segmentation of analytical STEM datasets |
| title_sort | on the use of clustering workflows for automated microstructure segmentation of analytical stem datasets |
| url | http://dx.doi.org/10.1063/5.0246329 |
| work_keys_str_mv | AT zhiquankho ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets AT andybridger ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets AT keithbutler ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets AT ercincduran ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets AT mohsendanaie ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets AT alexanderseggeman ontheuseofclusteringworkflowsforautomatedmicrostructuresegmentationofanalyticalstemdatasets |