Open AccessMachine Learning: Direct Prediction of Phonon Density of States With Euclidean Neural Networks (Adv. Sci. 12/2021)
Author(s) -
Chen Zhantao,
Andrejevic Nina,
Smidt Tess,
Ding Zhiwei,
Xu Qian,
Chi YenTing,
Nguyen Quynh T.,
Alatas Ahmet,
Kong Jing,
Li Mingda
Publication year - 2021
Publication title -
advanced science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.388
H-Index - 100
ISSN - 2198-3844
DOI - 10.1002/advs.202170068
Subject(s) - phonon , artificial neural network , measure (data warehouse) , ab initio , work (physics) , condensed matter physics , thermal , euclidean geometry , symmetry (geometry) , density of states , materials science , statistical physics , physics , computer science , machine learning , mathematics , quantum mechanics , thermodynamics , data mining , geometry
Phonon density‐of‐states is a key property that governs materials thermal properties but is nontrivial to compute or measure. A neural network that carries full crystal symmetry allows a prediction of phonon density‐of‐states using a small volume of training data, approaching ab initio accuracy but with significantly increased efficiency, as demonstrated in article number 2004214, by Mingda Li, Zhantao Chen, Nina Andrejevic, Tess Smidt, and co‐workers. This work enables direct structure‐property design of materials with superior thermal properties.