Graph neural networks (GNNs) present a promising route for machine learning of solid-state materials’ properties, but methods capable of directly predicting defect properties from ideal, defect-free structures are needed. A GNN developed for direct defect property predictions enables high-throughput screening of redox-active oxides for energy applications and beyond.
This is a preview of subscription content, log in via an institution to check access.
References
McDaniel, A. H. Renewable energy carriers derived from concentrating solar power and nonstoichiometric oxides. Curr. Opin. Green Sustain. 4, 37–43 (2017). A review article offering a perspective on the state of solar thermochemical gas splitting.
Goyal, A., Gorai, P., Peng, H., Lany, S. & Stevanovic, V. A computational framework for automation of point defect calculations. Comput. Mater. Sci. 130, 1–9 (2017). This paper describes a high-throughput approach to supercell defect calculations.
Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018). This work introduces the Crystal Graph Convolutional Neutral Networks as a machine learning approach for crystalline materials.
Lany, S. Communication: the electronic entropy of charged defect formation and its impact on thermochemical redox cycles. J. Chem. Phys. 148, 071101 (2018). This article presents an analysis of the effect of the solid-state reduction entropy on thermochemical gas-phase equilibria.
Wexler, R. B., Gautam, G. S., Stechel, E. B. & Carter, E. A. Factors governing oxygen vacancy formation in oxide perovskites. J. Am. Chem. Soc. 143, 13212–13227 (2021). This paper describes linear models to predict oxygen defect formation enthalpies.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Witman, M. D. et al. Defect graph neural networks for materials discovery in high-temperature clean-energy applications. Nat. Comput. Sci. https://doi.org/10.1038/s43588-023-00495-2 (2023).
Rights and permissions
About this article
Cite this article
Energy materials screening with defect graph neural networks. Nat Comput Sci 3, 671–672 (2023). https://doi.org/10.1038/s43588-023-00510-6
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-023-00510-6
- Springer Nature America, Inc.