Defect Graph Neural Networks for Materials Discovery in High-Temperature Clean-Energy Applications

Matthew Witman, Anuj Goyal, Tadashi Ogitsu, Anthony McDaniel, Stephan Lany

Research output: Contribution to journalArticlepeer-review

9 Scopus Citations


We present a graph neural network approach that fully automates the prediction of defect formation enthalpies for any crystallographic site from the ideal crystal structure, without the need to create defected atomic structure models as input. Here we used density functional theory reference data for vacancy defects in oxides, to train a defect graph neural network (dGNN) model that replaces the density functional theory supercell relaxations otherwise required for each symmetrically unique crystal site. Interfaced with thermodynamic calculations of reduction entropies and associated free energies, the dGNN model is applied to the screening of oxides in the Materials Project database, connecting the zero-kelvin defect enthalpies to high-temperature process conditions relevant for solar thermochemical hydrogen production and other energy applications. The dGNN approach is applicable to arbitrary structures with an accuracy limited principally by the amount and diversity of the training data, and it is generalizable to other defect types and advanced graph convolution architectures. It will help to tackle future materials discovery problems in clean energy and beyond.

Original languageAmerican English
Pages (from-to)675-686
Number of pages12
JournalNature Computational Science
Issue number8
StatePublished - 2023

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Nature America, Inc.

NREL Publication Number

  • NREL/JA-5K00-84167


  • machine learning
  • solar thermochemical hydrogen


Dive into the research topics of 'Defect Graph Neural Networks for Materials Discovery in High-Temperature Clean-Energy Applications'. Together they form a unique fingerprint.

Cite this