Title: Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

Abstract

The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 10⁴ data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Authors:

Xie, Tian ^[1]; Grossman, Jeffrey C. ^[1]

---

+ Show Author Affiliations

1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Materials Science and Engineering

Publication Date:

2018-04-06

Research Org.:

Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)

Sponsoring Org.:

USDOE Office of Science (SC)

OSTI Identifier:

1524040

Grant/Contract Number:  

AC02-05CH11231

Resource Type:

Accepted Manuscript

Journal Name:

Physical Review Letters

Additional Journal Information:

Journal Volume: 120; Journal Issue: 14; Journal ID: ISSN 0031-9007

Publisher:

American Physical Society (APS)

Country of Publication:

United States

Language:

English

Subject:

36 MATERIALS SCIENCE