Predicting ionic conductivity in solids from the machine-learned potential energy landscape
Physical Review Research · 19.05.2025 · 7 (2)
DOI: 10.1103/physrevresearch.7.023167 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Research, online erschienen am 19.05.2025. Verfasst von Artem Maevskiy und 7 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education - Singapore, National University of Singapore, National Research Foundation Singapore.
Abstract (Originalsprache)
Discovering new superionic materials is essential for advancing solid-state batteries, which offer improved energy density and safety compared to traditional lithium-ion batteries with liquid electrolytes. Conventional computational methods for identifying such materials are resource-intensive and not easily scalable. Recently, universal interatomic potential models have been developed using equivariant graph neural networks. These models are trained on extensive datasets of first-principles force and energy calculations. One can achieve significant computational advantages by leveraging them as the foundation for traditional methods of assessing the ionic conductivity, such as molecular dynamics or nudged elastic band techniques. However, the generalization error from model inference on diverse atomic structures arising in such calculations can compromise the reliability of the results. In this work, we propose an approach for the quick and reliable screening of ionic conductors through the analysis of a universal interatomic potential. Our method incorporates a set of heuristic structure descriptors that effectively employ the rich knowledge of the underlying model while requiring minimal generalization capabilities. Using our descriptors, we rank lithium-containing materials in the Materials Project database according to their expected ionic conductivity. Eight out of the ten highest-ranked materials are confirmed to be superionic at room temperature in first-principles calculations. Notably, our method achieves a speed-up factor of approximately 50 compared to molecular dynamics driven by a machine-learning potential, and it is at least 3000 times faster compared to first-principles molecular dynamics.
Förderung
- Ministry of Education - Singapore
- National University of Singapore
- National Research Foundation Singapore
- National Supercomputing Centre Singapore
Zitieren
APA
Maevskiy, A., Carvalho, A., Sataev, E., Turchyna, V., Noori, K., Rodin, A., Neto, A. H. C., & Ustyuzhanin, A. (2025). Predicting ionic conductivity in solids from the machine-learned potential energy landscape. Physical Review Research, 7(2). https://doi.org/10.1103/physrevresearch.7.023167
Vancouver
Maevskiy A, Carvalho A, Sataev E, Turchyna V, Noori K, Rodin A, et al. Predicting ionic conductivity in solids from the machine-learned potential energy landscape. Physical Review Research. 2025;7(2). doi:10.1103/physrevresearch.7.023167
BibTeX
@article{Maevskiy2025,
author = {Maevskiy, Artem and Carvalho, Alexandra and Sataev, Emil and Turchyna, Volha and Noori, Keian and Rodin, Aleksandr and Neto, A. H. Castro and Ustyuzhanin, Andrey},
title = {Predicting ionic conductivity in solids from the machine-learned potential energy landscape},
journal = {Physical Review Research},
year = {2025},
volume = {7},
number = {2},
doi = {10.1103/physrevresearch.7.023167}
}
EUVIMED