skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

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:
 [1];  [1]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Materials Science and Engineering
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory (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:
Journal Article: 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

Citation Formats

Xie, Tian, and Grossman, Jeffrey C. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. United States: N. p., 2018. Web. doi:10.1103/PhysRevLett.120.145301.
Xie, Tian, & Grossman, Jeffrey C. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. United States. https://doi.org/10.1103/PhysRevLett.120.145301
Xie, Tian, and Grossman, Jeffrey C. 2018. "Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties". United States. https://doi.org/10.1103/PhysRevLett.120.145301. https://www.osti.gov/servlets/purl/1524040.
@article{osti_1524040,
title = {Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties},
author = {Xie, Tian and Grossman, Jeffrey C.},
abstractNote = {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.},
doi = {10.1103/PhysRevLett.120.145301},
url = {https://www.osti.gov/biblio/1524040}, journal = {Physical Review Letters},
issn = {0031-9007},
number = 14,
volume = 120,
place = {United States},
year = {Fri Apr 06 00:00:00 EDT 2018},
month = {Fri Apr 06 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 724 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Deep learning
journal, May 2015


Accelerated search for materials with targeted properties by adaptive design
journal, April 2016


The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
journal, December 2015


Voronoi–dirichlet polyhedra in crystal chemistry: theory and applications
journal, October 2004


Charting the complete elastic properties of inorganic crystalline compounds
journal, March 2015


An Interpretation of Bond Lengths and a Classification of Bonds
journal, December 1951


An Explanation of Chemical Variations within Periodic Major Groups
journal, October 1952


Crystal structure representations for machine learning models of formation energies
journal, April 2015


Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013


Electron correlation in semiconductors and insulators: Band gaps and quasiparticle energies
journal, October 1986


Representation of compounds for machine-learning prediction of physical properties
journal, April 2017


How to represent crystal structures for machine learning: Towards fast prediction of electronic properties
journal, May 2014


Computational screening of perovskite metal oxides for optimal solar light capture
journal, January 2012


Big Data of Materials Science: Critical Role of the Descriptor
journal, March 2015


A high-throughput infrastructure for density functional theory calculations
journal, June 2011


Machine Learning Energies of 2 Million Elpasolite ( A B C 2 D 6 ) Crystals
journal, September 2016


The Inorganic Crystal Structure Database (ICSD)—Present and Future
journal, January 2004


Universal fragment descriptors for predicting properties of inorganic crystals
journal, June 2017


Materials Cartography: Representing and Mining Materials Space Using Structural and Electronic Fingerprints
journal, January 2015


The thermodynamic scale of inorganic crystalline metastability
journal, November 2016


Covalent radii revisited
journal, January 2008


Cubic lead perovskite PbMoO 3 with anomalous metallic behavior
journal, April 2017


Phase Transitions in Solid Solutions of PbZrO 3 and PbTiO 3 (II) X-ray Study
journal, January 1952


Universal fragment descriptors for predicting properties of inorganic crystals
text, January 2017


Crystal structure representations for machine learning models of formation energies
text, January 2015


Deep Learning
text, January 2018


The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
text, January 2015


Big Data of Materials Science - Critical Role of the Descriptor
text, January 2014


Works referencing / citing this record:

Thermodynamic Stability Landscape of Halide Double Perovskites via High-Throughput Computing and Machine Learning
journal, January 2019


Predicting Thermal Properties of Crystals Using Machine Learning
journal, December 2019


Data‐Driven Materials Science: Status, Challenges, and Perspectives
journal, September 2019


A Critical Review of Machine Learning of Energy Materials
journal, January 2020


Band Gap Prediction for Large Organic Crystal Structures with Machine Learning
journal, July 2019


Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering
journal, August 2018


Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials
journal, June 2019


Recent advances and applications of machine learning in solid-state materials science
journal, August 2019


Graph similarity drives zeolite diffusionless transformations and intergrowth
journal, October 2019


A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems
journal, September 2019


Machine learning material properties from the periodic table using convolutional neural networks
journal, January 2018


Extensive deep neural networks for transferring small scale learning to large scale systems
journal, January 2019


New horizons in thermoelectric materials: Correlated electrons, organic transport, machine learning, and more
journal, May 2019


Machine learning for interatomic potential models
journal, February 2020


Predicting HSE band gaps from PBE charge densities via neural network functionals
journal, January 2020


From DFT to machine learning: recent approaches to materials science–a review
journal, May 2019


New tolerance factor to predict the stability of perovskite oxides and halides
journal, February 2019


Inverse design of porous materials using artificial neural networks
journal, January 2020


Crystal symmetry determination in electron diffraction using machine learning
journal, January 2020


Deep materials informatics: Applications of deep learning in materials science
journal, June 2019


Data‐Driven Materials Science: Status, Challenges, and Perspectives
journal, November 2019


New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
text, January 2018


Data-driven materials science: status, challenges and perspectives
text, January 2019