Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery

Cheol Woo Park, Chris Wolverton

Research output: Contribution to journalArticlepeer-review

220 Scopus citations

Abstract

The recently proposed crystal graph convolutional neural network (CGCNN) offers a highly versatile and accurate machine learning (ML) framework by learning material properties directly from graphlike representations of crystal structures ("crystal graphs"). Here, we develop an improved variant of the CGCNN model (iCGCNN) that outperforms the original by incorporating information of the Voronoi tessellated crystal structure, explicit three-body correlations of neighboring constituent atoms, and an optimized chemical representation of interatomic bonds in the crystal graphs. We demonstrate the accuracy of the improved framework in two distinct illustrations: First, when trained/validated on 180 000/20 000 density functional theory (DFT) calculated thermodynamic stability entries taken from the Open Quantum Materials Database (OQMD) and evaluated on a separate test set of 230 000 entries, iCGCNN achieves a predictive accuracy that is significantly improved, i.e., 20% higher than that of the original CGCNN. Second, when used to assist a high-throughput search for materials in the ThCr2Si2 structure-type, iCGCNN exhibited a success rate of 31% which is 155 times higher than an undirected high-throughput search and 2.4 times higher than that of the original CGCNN. Using both CGCNN and iCGCNN, we screened 132 600 compounds with elemental decorations of the ThCr2Si2 prototype crystal structure and identified a total of 97 unique stable compounds by performing 757 DFT calculations, accelerating the computational time of the high-throughput search by a factor of 65. Our results suggest that the iCGCNN can be used to accelerate high-throughput discoveries of new materials by quickly and accurately identifying crystalline compounds with properties of interest.

Original languageEnglish (US)
Article number063801
JournalPhysical Review Materials
Volume4
Issue number6
DOIs
StatePublished - Jun 2020

Funding

This work was performed under the following financial assistance: Award No. 70NANB14H012 from US Department of Commerce, National Institute of Standards and Technology as part of the Center for Hierarchical Materials Design (CHiMaD). The authors also acknowledge the financial support of Toyota Research Institute (TRI). This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation Grant No. ACI-1548562. This work was also supported in part through the computational resources and staff contributions provided for the Quest high performance computing facility at Northwestern University which is jointly supported by the Office of the Provost, the Office for Research, and Northwestern University Information Technology. The authors thank V. Hegde, E. Isaacs, M. Liu, S. Griesemer, A. Gopakumar, and K. Pal for helpful discussion.

ASJC Scopus subject areas

  • General Materials Science
  • Physics and Astronomy (miscellaneous)

Fingerprint

Dive into the research topics of 'Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery'. Together they form a unique fingerprint.

Cite this