A graph neural network using virtual nodes is proposed to predict the properties of complex materials with variable dimensions or dimensions that depend on the input. The method is used to accurately and quickly predict phonon dispersion relations in complex solids and alloys.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Reiser, P. et al. Graph neural networks for materials science and chemistry. Comput. Mater. 3, 93 (2022). A review article describing the basics of graph neural networks.
Baroni, S. et al. Phonons and related crystal properties from density-functional perturbation theory. Rev. Modern Phys. 73, 515 (2001). This paper describes DFPT, which is the orthodox approach for calculating phonon dispersion relations.
Chen, C. & Ong, S. P. A universal graph deep learning interatomic potential for the periodic table. Nat. Comput. Sci. 2, 718–728 (2022). This paper outlines a state-of-the-art machine learning interatomic potential.
Petretto, G. et al. High-throughput density-functional perturbation theory phonons for inorganic materials. Sci. Data 5, 180065 (2018). This database was used to provide training data for our virtual node GNN.
Chen, Z. et al. Direct prediction of phonon density of states with Euclidean neural networks. Adv. Sci. 8, 2004214 (2021). This paper describes a machine-learning model that predicts the phonon density-of-states from crystal structures.
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: Okabe, R. et al. Virtual node graph neural network for full phonon prediction. Nat. Comput. Sci. https://doi.org/10.1038/s43588-024-00661-0 (2024).
Rights and permissions
About this article
Cite this article
Boosting graph neural networks with virtual nodes to predict phonon properties. Nat Comput Sci 4, 481–482 (2024). https://doi.org/10.1038/s43588-024-00665-w
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s43588-024-00665-w
