Deep Learning Enables Rapid Identification of a New Quasicrystal from Multiphase Powder Diffraction Patterns

Hirotaka Uryu; Tsunetomo Yamada; Koichi Kitahara; Alok Singh; Yutaka Iwasaki; Kaoru Kimura; Kanta Hiroki; Naoki Miyao; Asuka Ishikawa; Ryuji Tamura; Satoshi Ohhashi; Chang Liu; Ryo Yoshida

doi:10.1002/advs.202304546

Journal article Deep Learning Enables Rapid Identification of a New Quasicrystal from Multiphase Powder Diffraction Patterns

; ; ;

;

; ; ; ; ; ; ;

Advanced Science - 2023 - Uryu - Deep Learning Enables Rapid Identification of a New Quasicrystal from Multiphase Powder.pdf

Download file (1.83 MB)
Download as zip (1.24 MB)

Collection

Citation

Hirotaka Uryu, Tsunetomo Yamada, Koichi Kitahara, Alok Singh, Yutaka Iwasaki, Kaoru Kimura, Kanta Hiroki, Naoki Miyao, Asuka Ishikawa, Ryuji Tamura, Satoshi Ohhashi, Chang Liu, Ryo Yoshida. Deep Learning Enables Rapid Identification of a New Quasicrystal from Multiphase Powder Diffraction Patterns. Advanced Science. 2023, 11 (1), 2304546. https://doi.org/10.1002/advs.202304546

(BibTeX)

Description:

(abstract)

Since the discovery of the quasicrystal, approximately 100 stable quasicrystalsare identiﬁed. To date, the existence of quasicrystals is veriﬁed usingtransmission electron microscopy; however, this technique requiressigniﬁcantly more elaboration than rapid and automatic powder X-raydiﬀraction. Therefore, to facilitate the search for novel quasicrystals,developing a rapid technique for phase-identiﬁcation from powder diﬀractionpatterns is desirable. This paper reports the identiﬁcation of a new Al–Si–Ruquasicrystal using deep learning technologies from multiphase powderpatterns, from which it is diﬃcult to discriminate the presence ofquasicrystalline phases even for well-trained human experts. Deep neuralnetworks trained with artiﬁcially generated multiphase powder patternsdetermine the presence of quasicrystals with an accuracy >92% from actualpowder patterns. Speciﬁcally, 440 powder patterns are screened using thetrained classiﬁer, from which the Al–Si–Ru quasicrystal is identiﬁed. Thisstudy demonstrates an excellent potential of deep learning to identify anunknown phase of a targeted structure from powder patterns even whenexisting in a multiphase sample.

Rights:

Creative Commons BY Attribution 4.0 International

Keyword: deep learning, x-ray powder diffraction, quasicrystal, phase identification, machine learning

Date published: 2023-11-14

Publisher: Wiley

Journal:

Advanced Science (ISSN: 21983844) vol. 11 issue. 1 2304546

Funding:

Japan Society for the Promotion of Science 19H05820
Japan Society for the Promotion of Science 19H05818
Core Research for Evolutional Science and Technology JPMJCR19I3
Core Research for Evolutional Science and Technology JPMJCR22O3

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1002/advs.202304546

Related item:

Other identifier(s):

Contact agent:

Updated at: 2024-12-13 12:30:39 +0900

Published on MDR: 2024-12-13 12:30:39 +0900

Filename	Size
Filename	Advanced Science - 2023 - Uryu - Deep Learning Enables Rapid Identification of a New Quasicrystal from Multiphase Powder.pdf (Thumbnail) application/pdf	Size	1.83 MB	Detail