Artificial neural network for the configuration problem in solids

被引:10
|
作者
Ji, Hyunjun [1 ]
Jung, Yousung [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Grad Sch EEWS, 291 Daehak Ro, Daejeon 34141, South Korea
来源
JOURNAL OF CHEMICAL PHYSICS | 2017年 / 146卷 / 06期
基金
新加坡国家研究基金会;
关键词
POTENTIAL-ENERGY SURFACES; MOLECULAR-MECHANICS; MOVTENBO CATALYSTS; FORCE-FIELD; PHASE; APPROXIMATION; CHEMISTRY; ACCURATE; STORAGE; M1;
D O I
10.1063/1.4974928
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
A machine learning approach based on the artificial neural network (ANN) is applied for the configuration problem in solids. The proposed method provides a direct mapping from configuration vectors to energies. The benchmark conducted for the M1 phase of Mo-V-Te-Nb oxide showed that only a fraction of configurations needs to be calculated, thus the computational burden significantly decreased, by a factor of 20-50, with R-2 = 0.96 and MAD = 0.12 eV. It is shown that ANN can also handle the effects of geometry relaxation when properly trained, resulting in R-2 = 0.95 and MAD = 0.13 eV. Published by AIP Publishing.
引用
收藏
页数:11
相关论文
共 50 条