Study on Prediction of Crystal Properties Based on Deep Learning

Authors

Buwei Wang, 1. College of Information Engineering, Yangzhou University, Yangzhou 225127, China; ;
Wang Min, 2. School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China;
Fan Qian, 1. College of Information Engineering, Yangzhou University, Yangzhou 225127, China; ;
Ya'nan Wang, 1. College of Information Engineering, Yangzhou University, Yangzhou 225127, China; ;
hanwen zhang, 1. College of Information Engineering, Yangzhou University, Yangzhou 225127, China; ;
Yunliang Yue, 1. College of Information Engineering, Yangzhou University, Yangzhou 225127, China; ;

Abstract

Abstract: Predicting crystal properties using traditional machine learning methods requires complex feature engineering. In order to bypass time-consuming feature engineering, element network (ElemNet), representation learning from stoichiometry (Roost), compositionally-restricted attention-based network (CrabNet) and crystal graph convolution neural network (CGCNN) based on deep learning technology are used to simulate the formation energy, total energy per atom, band gap, and Fermi energy of crystal. The residual learning is introduced into CGCNN, and a crystal graph convolution residual neural network (CGCRN) is proposed. In the CGCRN, the number of hidden layers and the number of nodes in the hidden layers are increased, and the hidden layers are connected by residual connection. Meanwhile, the BatchNorm layers are added for normalization. Compared with CGCNN, the prediction accuracy of 4 physical quantities using CGCRN has increased by 1.3%~4.8%, which is conducive to rapid and accurate prediction of ideal crystal materials.

Recommended Citation

Wang, Buwei; Min, Wang; Qian, Fan; Wang, Ya'nan; zhang, hanwen; and Yue, Yunliang (2022) "Study on Prediction of Crystal Properties Based on Deep Learning," Journal of System Simulation: Vol. 33: Iss. 12, Article 10.
DOI: 10.16182/j.issn1004731x.joss.21-FZ0772
Available at: https://dc-china-simulation.researchcommons.org/journal/vol33/iss12/10

First Page

2854

Revised Date

2021-07-29

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.21-FZ0772

Last Page

2863

CLC

TP183;TP391

Recommended Citation

Wang Buwei, Wang Min, Fan Qian, Wang Ya'nan, zhang hanwen, Yue Yunliang. Study on Prediction of Crystal Properties Based on Deep Learning[J]. Journal of System Simulation, 2021, 33(12): 2854-2863.

Corresponding Author

Yunliang Yue,

DOI

10.16182/j.issn1004731x.joss.21-FZ0772