Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning

We analyzed a number of complicated X-ray diffraction patterns using feature patterns obtained through unsupervised machine learning. A crystalline SiGe film on a Si substrate with a spatial fluctuation in both composition and crystal orientation was tested as a model sample having complicated X-ray...

Full description

Saved in:
Bibliographic Details
Main Authors: Kentaro Kutsukake, Takefumi Kamioka, Kota Matsui, Ichiro Takeuchi, Takashi Segi, Takuo Sasaki, Seiji Fujikawa, Masamitu Takahasi
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Science and Technology of Advanced Materials: Methods
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/27660400.2024.2336402
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846129055484608512
author Kentaro Kutsukake
Takefumi Kamioka
Kota Matsui
Ichiro Takeuchi
Takashi Segi
Takuo Sasaki
Seiji Fujikawa
Masamitu Takahasi
author_facet Kentaro Kutsukake
Takefumi Kamioka
Kota Matsui
Ichiro Takeuchi
Takashi Segi
Takuo Sasaki
Seiji Fujikawa
Masamitu Takahasi
author_sort Kentaro Kutsukake
collection DOAJ
description We analyzed a number of complicated X-ray diffraction patterns using feature patterns obtained through unsupervised machine learning. A crystalline SiGe film on a Si substrate with a spatial fluctuation in both composition and crystal orientation was tested as a model sample having complicated X-ray diffraction patterns with multipeaks. Non-negative matrix factorization (NMF), an unsupervised machine learning method, was performed on 961 patterns obtained by spatial mapping of micro-beam X-ray diffraction measurements. Among the tested number of the feature patterns from 1 to 10, four feature patterns were the most useful for extracting the information about the composition and crystal orientation because they correspond to the diffraction patterns of typical SiGe films with high and low Si fraction, and right- and left-tilted orientation. Reasonable spatial maps of composition and crystal orientation were visualized using coefficients of the four feature patterns. Furthermore, the spatial constraint was tested for NMF using 225 diffraction patterns which were down-sized from 33 × 33 to 16 × 16 pixels due to the high computational cost of simple implementation without techniques to reduce the cost. Four feature patterns similar to those of the simple NMF without the constraints and the more reasonable distribution reflecting the SiGe spatial domain structure were obtained. The feature pattern extraction by NMF and interpretation by experts demonstrated in this study will be useful for quick analysis of a number of X-ray diffraction patterns with large and complicated fluctuations.
format Article
id doaj-art-c5fd43a7b7414262a9bc15bb30fbf8c3
institution Kabale University
issn 2766-0400
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Science and Technology of Advanced Materials: Methods
spelling doaj-art-c5fd43a7b7414262a9bc15bb30fbf8c32024-12-10T09:58:05ZengTaylor & Francis GroupScience and Technology of Advanced Materials: Methods2766-04002024-12-014110.1080/27660400.2024.2336402Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learningKentaro Kutsukake0Takefumi Kamioka1Kota Matsui2Ichiro Takeuchi3Takashi Segi4Takuo Sasaki5Seiji Fujikawa6Masamitu Takahasi7Center for Advanced Intelligence Project, RIKEN, Tokyo, JapanMeiji University, Kawasaki, JapanGraduate School of Medicine, Nagoya University, Nagoya, JapanCenter for Advanced Intelligence Project, RIKEN, Tokyo, JapanComputational Science Department, KOBELCO RESEARCH INSTITUTE, INC, Kobe, JapanSynchrotron Radiation Research Center, National Institutes for Quantum Science and Technology, Hyogo, JapanSynchrotron Radiation Research Center, National Institutes for Quantum Science and Technology, Hyogo, JapanSynchrotron Radiation Research Center, National Institutes for Quantum Science and Technology, Hyogo, JapanWe analyzed a number of complicated X-ray diffraction patterns using feature patterns obtained through unsupervised machine learning. A crystalline SiGe film on a Si substrate with a spatial fluctuation in both composition and crystal orientation was tested as a model sample having complicated X-ray diffraction patterns with multipeaks. Non-negative matrix factorization (NMF), an unsupervised machine learning method, was performed on 961 patterns obtained by spatial mapping of micro-beam X-ray diffraction measurements. Among the tested number of the feature patterns from 1 to 10, four feature patterns were the most useful for extracting the information about the composition and crystal orientation because they correspond to the diffraction patterns of typical SiGe films with high and low Si fraction, and right- and left-tilted orientation. Reasonable spatial maps of composition and crystal orientation were visualized using coefficients of the four feature patterns. Furthermore, the spatial constraint was tested for NMF using 225 diffraction patterns which were down-sized from 33 × 33 to 16 × 16 pixels due to the high computational cost of simple implementation without techniques to reduce the cost. Four feature patterns similar to those of the simple NMF without the constraints and the more reasonable distribution reflecting the SiGe spatial domain structure were obtained. The feature pattern extraction by NMF and interpretation by experts demonstrated in this study will be useful for quick analysis of a number of X-ray diffraction patterns with large and complicated fluctuations.https://www.tandfonline.com/doi/10.1080/27660400.2024.2336402X-ray diffraction patternmachine learningnon-negative matrix factorizationmicro beam mappingsynchrotron radiation
spellingShingle Kentaro Kutsukake
Takefumi Kamioka
Kota Matsui
Ichiro Takeuchi
Takashi Segi
Takuo Sasaki
Seiji Fujikawa
Masamitu Takahasi
Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
Science and Technology of Advanced Materials: Methods
X-ray diffraction pattern
machine learning
non-negative matrix factorization
micro beam mapping
synchrotron radiation
title Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
title_full Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
title_fullStr Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
title_full_unstemmed Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
title_short Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning
title_sort feature extraction and spatial imaging of synchrotron radiation x ray diffraction patterns using unsupervised machine learning
topic X-ray diffraction pattern
machine learning
non-negative matrix factorization
micro beam mapping
synchrotron radiation
url https://www.tandfonline.com/doi/10.1080/27660400.2024.2336402
work_keys_str_mv AT kentarokutsukake featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT takefumikamioka featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT kotamatsui featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT ichirotakeuchi featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT takashisegi featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT takuosasaki featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT seijifujikawa featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning
AT masamitutakahasi featureextractionandspatialimagingofsynchrotronradiationxraydiffractionpatternsusingunsupervisedmachinelearning