Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN

Wu, Zhendong; Hayashi, Yusuke; Tohei, Tetsuya; Sumitani, Kazushi; Imai, Yasuhiko; Kimura, Shigeru; Sakai, Akira

doi:https://doi.org/10.1107/S1600576725004169

Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN

Wu, Zhendong; Hayashi, Yusuke; Tohei, Tetsuya et al.

Journal of Applied Crystallography, 2025, 58, 1205-1219

Number of Access:9（2025-09-03 12:06 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/102636

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
JApplCrystallog_58_1205	pdf	None	11.5 MB	7	2025.08.29

Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title	Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN
Creator	CreatorName Wu, Zhendong
	NRID 1000000800484 1000000800484 CreatorName Hayashi, Yusuke
	NRID 1000000463878 1000000463878 ORCID 0000-0002-4113-2566 0000-0002-4113-2566 researchmap permalink ttohei ttohei Scopus Author ID 55880985600 55880985600 CreatorName Tohei, Tetsuya
	NRID 1000010416381 1000010416381 CreatorName Sumitani, Kazushi
	NRID 1000030416375 1000030416375 CreatorName Imai, Yasuhiko
	NRID 1000050360821 1000050360821 CreatorName Kimura, Shigeru
	NRID 1000020314031 1000020314031 ORCID 0000-0002-0654-504X 0000-0002-0654-504X researchmap permalink read0192520 read0192520 Scopus Author ID 7402911242 7402911242 CreatorName Sakai, Akira
Subject	crystal growth
	HVPE GaN wafers
	hydride vapor-phase epitaxy films
	machine learning
	nanoXRD
	X-ray diffraction
Description	Wu Z., Hayashi Y., Tohei T., et al. Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN. Journal of Applied Crystallography 58, 1205 (2025); https://doi.org/10.1107/S1600576725004169.
Abstract	Nanobeam X-ray diffraction (nanoXRD) is a powerful tool for collecting in situ crystal structure information with high spatial resolution and data acquisition rate. However, analyzing the enormous amount of data produced by these high-throughput experiments for defect recognition or discovering hidden structural features becomes challenging. Machine learning (ML) methods have become attractive recently due to their outstanding performance in analyzing large data sets. This research utilizes an ML algorithm, uniform manifold approximation and projection (UMAP), to enhance the nanoXRD-based crystal structure analysis of a cross-sectional hydride vapor-phase epitaxy GaN wafer. Compared with the results obtained by conventional fitting, UMAP gives a more precise categorization of crystal structure based on the raw three-dimensional !–2θ–’ diffraction patterns. The property that UMAP embeds the high-dimensional data while retaining the data structure is valuable in guiding the analysis of nanoXRD profiles. This research also demonstrates the capability of UMAP in analyzing other spectroscopic or diffraction data sets to guide crystal structure investigations.
Publisher	International Union of Crystallography
Source Title	Journal of Applied Crystallography
Volume (Issue)	58
Page	1205-1219
Date of Issued	2025-07-08
Language	English
Handle URL	https://hdl.handle.net/11094/102636
PISSN	00218898
eISSN	16005767
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1107/S1600576725004169
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCMI Type	Text
DCTERMS.bibliographicCitation	Journal of Applied Crystallography. 2025, 58, p. 1205-1219
DC.title	Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN
DC.creator	Wu, Zhendong
	Hayashi, Yusuke
	Tohei, Tetsuya
	Sumitani, Kazushi
	Imai, Yasuhiko
	Kimura, Shigeru
	Sakai, Akira
DC.publisher	International Union of Crystallography
DC.language' scheme='DCTERMS.RFC1766	English
DC.type' scheme='DCTERMS.DCMIType	Text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-07-08
DC.identifier	https://doi.org/10.1107/S1600576725004169
DC.subject	crystal growth
	HVPE GaN wafers
	hydride vapor-phase epitaxy films
	machine learning
	nanoXRD
	X-ray diffraction
DC.description	Wu Z., Hayashi Y., Tohei T., et al. Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN. Journal of Applied Crystallography 58, 1205 (2025); https://doi.org/10.1107/S1600576725004169.
DCTERMS.abstract	Nanobeam X-ray diffraction (nanoXRD) is a powerful tool for collecting in situ crystal structure information with high spatial resolution and data acquisition rate. However, analyzing the enormous amount of data produced by these high-throughput experiments for defect recognition or discovering hidden structural features becomes challenging. Machine learning (ML) methods have become attractive recently due to their outstanding performance in analyzing large data sets. This research utilizes an ML algorithm, uniform manifold approximation and projection (UMAP), to enhance the nanoXRD-based crystal structure analysis of a cross-sectional hydride vapor-phase epitaxy GaN wafer. Compared with the results obtained by conventional fitting, UMAP gives a more precise categorization of crystal structure based on the raw three-dimensional !–2θ–’ diffraction patterns. The property that UMAP embeds the high-dimensional data while retaining the data structure is valuable in guiding the analysis of nanoXRD profiles. This research also demonstrates the capability of UMAP in analyzing other spectroscopic or diffraction data sets to guide crystal structure investigations.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	102636
citation_title	Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN
citation_author	Wu, Zhendong
	Hayashi, Yusuke
	Tohei, Tetsuya
	Sumitani, Kazushi
	Imai, Yasuhiko
	Kimura, Shigeru
	Sakai, Akira
citation_publisher	International Union of Crystallography
citation_language	English
citation_date	2025-07-08
citation_journal_title	Journal of Applied Crystallography
citation_volume	58
citation_firstpage	1205
citation_lastpage	1219
citation_doi	https://doi.org/10.1107/S1600576725004169
citation_public_url	https://hdl.handle.net/11094/102636

Machine learning assisted nanobeam X-ray diffraction based analysis on hydride vapor-phase epitaxy GaN

Link to primary information

Item Information

Show details