It is difficult to identify stable surface reconstructions of complex materials. Now a Monte Carlo sampling strategy is coupled with a machine learning interatomic potential that is iteratively improved via active learning during the search.
References
Auer, A. et al. Nat. Catal. 3, 797–803 (2020).
Polo-Garzon, F., Bao, Z., Zhang, X., Huang, W. & Wu, Z. ACS Catal. 9, 5692–5707 (2019).
Xu, C. et al. Nat. Mater. 20, 84–92 (2021).
Du, X. et al. Nat. Comput. Sci. https://doi.org/10.1038/s43588-023-00571-7 (2023).
Bisbo, M. K. & Hammer, B. Phys. Rev. B 105, 245404 (2022).
Timmermann, J. et al. Phys. Rev. Lett. 125, 206101 (2020).
Wanzenböck, R. et al. Digital Discov. 1, 703–710 (2022).
Xu, J., Xie, W., Han, Y. & Hu, P. ACS Catal. 12, 14812–14824 (2022).
Mortensen, H. L., Meldgaard, S. A., Bisbo, M. K., Christiansen, M.-P. V. & Hammer, B. Phys. Rev. B 102, 075427 (2020).
Wang, Q., Oganov, A. R., Zhu, Q. & Zhou, X.-F. Phys. Rev. Lett. 113, 266101 (2014).
Wexler, R. B., Qiu, T. & Rappe, A. M. J. Phys. Chem. C 123, 2321–2328 (2019).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Andersen, M. Machine learning speeds up search for surface structure. Nat Comput Sci 3, 1009–1010 (2023). https://doi.org/10.1038/s43588-023-00575-3
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43588-023-00575-3
- Springer Nature America, Inc.