Unsupervised machine learning and cepstral analysis with 4D-STEM for characterizing complex microstructures of metallic alloys

Four-dimensional scanning transmission electron microscopy, coupled with a wide array of data analytics, has unveiled new insights into complex materials. Here, we introduce a straightforward unsupervised machine learning approach that entails dimensionality reduction and clustering with minimal hyp...

Full description

Saved in:
Bibliographic Details
Published in:npj computational materials 2024-09, Vol.10 (1), p.223-10, Article 223
Main Authors: Yoo, Timothy, Hershkovitz, Eitan, Yang, Yang, da Cruz Gallo, Flávia, Manuel, Michele V., Kim, Honggyu
Format: Article
Language:English
Subjects:
639/301/1023/1026
639/301/930/328/2082
Alloys
Automation
Case studies
Cepstral analysis
Characterization and Evaluation of Materials
Chemistry and Materials Science
Clustering
Computational Intelligence
Data analysis
Datasets
Diffraction patterns
Dimensional analysis
Electron diffraction
Information processing
Learning algorithms
Machine learning
Martensitic transformations
Materials Science
Mathematical and Computational Engineering
Mathematical and Computational Physics
Mathematical Modeling and Industrial Mathematics
Observational learning
Scanning electron microscopy
Scanning transmission electron microscopy
Shape memory alloys
Temperature
Theoretical
Thickness
Transmission electron microscopy
Unsupervised learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Four-dimensional scanning transmission electron microscopy, coupled with a wide array of data analytics, has unveiled new insights into complex materials. Here, we introduce a straightforward unsupervised machine learning approach that entails dimensionality reduction and clustering with minimal hyperparameter tuning to semi-automatically identify unique coexisting structures in metallic alloys. Applying cepstral transformation to the original diffraction dataset improves this process by effectively isolating phase information from potential signal ambiguity caused by sample tilt and thickness variations, commonly observed in electron diffraction patterns. In a case study of a NiTiHfAl shape memory alloy, conventional scanning transmission electron microscopy imaging struggles to accurately identify a low-contrast precipitate at lower magnifications, posing challenges for microscale analyses. We find that our method efficiently separates multiple coherent structures while using objective means of determining hyperparameters. Furthermore, we demonstrate how the clustering result facilitates more robust strain mapping to provide immediate and quantitative structural insights.
ISSN:2057-3960
2057-3960
DOI:10.1038/s41524-024-01414-3