Predicting charge density distribution of materials using a local-environment-based graph convolutional network
Name
PhysRevB.100.184103.pdf
Description
Published version
Size
1.58 MB
Format
Adobe PDF
Checksum (MD5)
56a048535e3117685af7a8475f2ab466
Author(s)
Gong, Sheng
Xie, Tian
Zhu, Taishan
Wang, Shuo
Fadel, Eric R.
Grossman, Jeffrey C.
Date Issued
November 2019
Journal
Physical Review B
Publisher
American Physical Society (APS)
Citation
Gong, Sheng et al. “Predicting charge density distribution of materials using a local-environment-based graph convolutional network.” Physical Review B, 100, 18 (Noember 2019): 184103 © 2019 The Author(s)
Version
Final published version
Abstract
The electron charge density distribution of materials is one of the key quantities in computational materials science as theoretically it determines the ground state energy and practically it is used in many materials analyses. However, the scaling of density functional theory calculations with number of atoms limits the usage of charge-density-based calculations and analyses. Here we introduce a machine-learning scheme with local-environment-based graphs and graph convolutional neural networks to predict charge density on grid points from the crystal structure. We show the accuracy of this scheme through a comparison of predicted charge densities as well as properties derived from the charge density, and that the scaling is O(N). More importantly, the transferability is shown to be high with respect to different compositions and structures, which results from the explicit encoding of geometry.
MIT Department
Massachusetts Institute of Technology. Research Laboratory of Electronics
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1103/PHYSREVB.100.184103
