Various machine learning models have been developed in recent years for the discovery of crystal structures. Matbench Discovery, a new benchmark, offers an efficient way to identify the most promising architectures.
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 full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Riebesell, J. et al. Nat. Mach. Intell. https://doi.org/10.1038/s42256-025-01055-1 (2025).
Merchant, A. et al. Nature 624, 80–85 (2023).
Takamoto, S., Okanohara, D., Li, Q.-J. & Li, J. J. Mater. 9, 447–454 (2023).
Tang, H. et al. Nat. Comput. Sci. 5, 144–154 (2205).
Wang, H.-C., Botti, S. & Marques, M. A. L. npj Comput. Mater. 7, 12 (2021).
Glass, C. W., Oganov, A. R. & Hansen, N. Comput. Phys. Commun. 175, 713 (2006).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare that they do not have competing interests.
Rights and permissions
About this article
Cite this article
Li, J. Universal interatomic potentials shine in finding crystal structures. Nat Mach Intell 7, 985–986 (2025). https://doi.org/10.1038/s42256-025-01061-3
Published:
Issue date:
DOI: https://doi.org/10.1038/s42256-025-01061-3
