Phase Diagrams of Alloys and Their Hydrides via On-Lattice Graph Neural Networks and Limited Training Data

Witman, Matthew D.; Bartelt, Norman C; Ling, Sanliang; Guan, Pin-Wen; Way, Lauren; Allendorf, Mark D.; Stavila, Vitalie

Abstract

Efficient prediction of sampling-intensive thermodynamic properties is needed to evaluate material performance and permit high-throughput materials modeling for a diverse array of technology applications. To alleviate the prohibitive computational expense of high-throughput configurational sampling with density functional theory (DFT), surrogate modeling strategies like cluster expansion are many orders of magnitude more efficient but can be difficult to construct in systems with high compositional complexity. We therefore employ minimal-complexity graph neural network models that accurately predict and can even extrapolate to out-of-train distribution formation energies of DFT-relaxed structures from an ideal (unrelaxed) crystallographic representation. This enables the large-scale sampling necessary for various thermodynamic property predictions that may otherwise be intractable and can be achieved with small training data sets. Two exemplars, optimizing the thermodynamic stability of low-density high-entropy alloys and modulating the plateau pressure of hydrogen in metal alloys, demonstrate the power of this approach, which can be extended to a variety of materials discovery and modeling problems.

Citation

Witman, M. D., Bartelt, N. C., Ling, S., Guan, P.-W., Way, L., Allendorf, M. D., & Stavila, V. (2024). Phase Diagrams of Alloys and Their Hydrides via On-Lattice Graph Neural Networks and Limited Training Data. Journal of Physical Chemistry Letters, 15(5), 1500-1506. https://doi.org/10.1021/acs.jpclett.3c03369

• Journal Article Type: Article
• Acceptance Date: Jan 18, 2024
• Online Publication Date: Feb 1, 2024
• Publication Date: Feb 8, 2024
• Deposit Date: Feb 13, 2024
• Publicly Available Date: Feb 2, 2025
• Journal: The Journal of Physical Chemistry Letters
• Electronic ISSN: 1948-7185
• Publisher: American Chemical Society
• Peer Reviewed: Peer Reviewed
• Volume: 15
• Issue: 5
• Pages: 1500-1506
• DOI: https://doi.org/10.1021/acs.jpclett.3c03369
• Keywords: Alloys, Computer simulations, Density functional theory, Energy, Materials
• Public URL: https://nottingham-repository.worktribe.com/output/30927712
• Publisher URL: https://pubs.acs.org/doi/10.1021/acs.jpclett.3c03369