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

Hirotaka Uryu ; Tsunetomo Yamada ; Koichi Kitahara ; Alok Singh SAMURAI ORCID (National Institute for Materials Science) ; Yutaka Iwasaki SAMURAI ORCID (National Institute for Materials Science) ; Kaoru Kimura ORCID (National Institute for Materials Science) ; Kanta Hiroki ; Naoki Miyao ; Asuka Ishikawa ; Ryuji Tamura ; Satoshi Ohhashi ; Chang Liu ; Ryo Yoshida

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
SAMURAI

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:

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