Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
15
Series
Physical Review B, Volume 104, issue 10
Abstract
We develop a neuroevolution-potential (NEP) framework for generating neural network-based machine-learning potentials. They are trained using an evolutionary strategy for performing large-scale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source gpumd package, which can attain a computational speed over atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.Description
Funding Information: National Natural Science Foundation of China Academy of Finland Funding Information: Z.F. acknowledges the supports from the National Natural Science Foundation of China (NSFC) (No. 11974059). Z.Z. and Y.C. are grateful for the research computing facilities offered by ITS, HKU. Y.W., H.D., and T.A.-N. acknowledge the support from the Academy of Finland Centre of Excellence program QTF (Project No. 312298) and the computational resources provided by Aalto Science-IT project and Finland's IT Center for Science (CSC). Publisher Copyright: © 2021 American Physical Society.
Keywords
Other note
Citation
Fan, Z, Zeng, Z, Zhang, C, Wang, Y, Song, K, Dong, H, Chen, Y & Ala-Nissila, T 2021, 'Neuroevolution machine learning potentials : Combining high accuracy and low cost in atomistic simulations and application to heat transport', Physical Review B, vol. 104, no. 10, 104309. https://doi.org/10.1103/PhysRevB.104.104309