Premium
Machine Learning to Predict Quasicrystals from Chemical Compositions (Adv. Mater. 36/2021)
Author(s) -
Liu Chang,
Fujita Erina,
Katsura Yukari,
Inada Yuki,
Ishikawa Asuka,
Tamura Ryuji,
Kimura Kaoru,
Yoshida Ryo
Publication year - 2021
Publication title -
advanced materials
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 10.707
H-Index - 527
eISSN - 1521-4095
pISSN - 0935-9648
DOI - 10.1002/adma.202170284
Subject(s) - quasicrystal , materials science , mechanism (biology) , artificial intelligence , machine learning , statistical physics , condensed matter physics , computer science , physics , quantum mechanics
Quasicrystals In article number 2102507, Kaoru Kimura, Ryo Yoshida, and co‐workers demonstrate that machine‐learning algorithms can predict the chemical composition of new quasicrystals. Furthermore, analyzing the input–output relationships black‐boxed into the machine‐learning model, they successfully identify nontrivial empirical equations interpretable by humans that describe the conditions necessary for stable quasicrystal formation. This is the first step toward understanding the formation mechanism of quasicrystals, which has been long sought in quasicrystal research.