Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image

Kohira, Kazuya; Nakamura, Shota; Fukuda, Hiroki; Kyotani, Kazuhiro; Ogi, Hirotsugu

doi:https://doi.org/10.1016/j.scriptamat.2025.117115

Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image

Kohira, Kazuya; Nakamura, Shota; Fukuda, Hiroki et al.

Scripta Materialia, 2025, 274, 117115

アクセス数:2件（2026-02-16 16:45 集計）

固定URL: https://hdl.handle.net/11094/103701

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
ScriptaMater_274_117115	pdf	なし	2.18 MB	6	2026.02.06

Creative Commons : 表示 - 非営利 - 改変禁止

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image
著者	著者名 Kohira, Kazuya
	著者名 Nakamura, Shota
	ORCID 0009-0002-0738-285X 0009-0002-0738-285X 著者名 Fukuda, Hiroki
	著者名 Kyotani, Kazuhiro
	NRID 1000090252626 1000090252626 ORCID 0000-0002-9602-5194 0000-0002-9602-5194 researchmap permalink read0042771 read0042771 Scopus Author ID 35563683500 35563683500 著者名 Ogi, Hirotsugu
キーワード等	Average Young's modulus
	Deep learning
	Elastic constants
	Elasticity image
	Hexagonal
	Resonant ultrasound spectroscopy
内容	Kohira K., Nakamura S., Fukuda H., et al. Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image. Scripta Materialia 274, 117115 (2026); https://doi.org/10.1016/j.scriptamat.2025.117115.
抄録	We developed a deep learning (DL) framework based on convolutional neural networks (CNNs) to predict elastic constants of hexagonal materials by leveraging high image-recognition capability of CNNs. Resonant frequency data were converted into three-channel RGB images, referred to as ”elasticity images” for CNN training. Without mode identification, the trained models accurately predicted all five independent elastic constants. We reveal that the average Young modulus is a critical for classification of hexagonal materials based on their elasticity images. Furthermore, we extended the Blackman diagram, originally developed for cubic crystals, to hexagonal systems, enabling a substantial reduction of five-dimensional elastic-constant space. We then established a two-step DL scheme: first, classification using the average Young modulus, followed by regression of the five elastic constants in the classified average-Young-modulus class. The prediction error was approximately 5 % for the principal elastic constants and 1.5 % for the average Young modulus.
出版者	Acta Materialia Inc
収録物名	Scripta Materialia
巻(号)	274
ページ	117115
刊行年月	2025-12-03
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103701
PISSN	13596462
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1016/j.scriptamat.2025.117115
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Scripta Materialia. 2025, 274, p. 117115
DC.title	Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image
DC.creator	Kohira, Kazuya
	Nakamura, Shota
	Fukuda, Hiroki
	Kyotani, Kazuhiro
	Ogi, Hirotsugu
DC.publisher	Acta Materialia Inc
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-12-03
DC.identifier	https://doi.org/10.1016/j.scriptamat.2025.117115
DC.subject	Average Young's modulus
	Deep learning
	Elastic constants
	Elasticity image
	Hexagonal
	Resonant ultrasound spectroscopy
DC.description	Kohira K., Nakamura S., Fukuda H., et al. Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image. Scripta Materialia 274, 117115 (2026); https://doi.org/10.1016/j.scriptamat.2025.117115.
DCTERMS.abstract	We developed a deep learning (DL) framework based on convolutional neural networks (CNNs) to predict elastic constants of hexagonal materials by leveraging high image-recognition capability of CNNs. Resonant frequency data were converted into three-channel RGB images, referred to as ”elasticity images” for CNN training. Without mode identification, the trained models accurately predicted all five independent elastic constants. We reveal that the average Young modulus is a critical for classification of hexagonal materials based on their elasticity images. Furthermore, we extended the Blackman diagram, originally developed for cubic crystals, to hexagonal systems, enabling a substantial reduction of five-dimensional elastic-constant space. We then established a two-step DL scheme: first, classification using the average Young modulus, followed by regression of the five elastic constants in the classified average-Young-modulus class. The prediction error was approximately 5 % for the principal elastic constants and 1.5 % for the average Young modulus.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DC.format	103701
citation_title	Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image
citation_author	Kohira, Kazuya
	Nakamura, Shota
	Fukuda, Hiroki
	Kyotani, Kazuhiro
	Ogi, Hirotsugu
citation_publisher	Acta Materialia Inc
citation_language	英語
citation_date	2025-12-03
citation_journal_title	Scripta Materialia
citation_volume	274
citation_firstpage	117115
citation_doi	https://doi.org/10.1016/j.scriptamat.2025.117115
citation_public_url	https://hdl.handle.net/11094/103701

Two-step deep learning for decoding elastic constants of hexagonal-symmetry materials from resonant-spectrum image

閲覧可能ファイル

論文情報

論文詳細を表示