Stenczel, Tamás, El-Machachi, Zakariya, Liepuoniute, Guoda et al. (5 more authors) (2023) Machine-learned acceleration for molecular dynamics in CASTEP. Journal of Chemical Physics. 044803. ISSN 1089-7690
Abstract
Machine learning (ML) methods are of rapidly growing interest for materials modeling, and yet, the use of ML interatomic potentials for new systems is often more demanding than that of established density-functional theory (DFT) packages. Here, we describe computational methodology to combine the CASTEP first-principles simulation software with the on-the-fly fitting and evaluation of ML interatomic potential models. Our approach is based on regular checking against DFT reference data, which provides a direct measure of the accuracy of the evolving ML model. We discuss the general framework and the specific solutions implemented, and we present an example application to high-temperature molecular-dynamics simulations of carbon nanostructures. The code is freely available for academic research.
Metadata
Authors/Creators: |
|
||||
---|---|---|---|---|---|
Copyright, Publisher and Additional Information: | © Author(s) 2023 | ||||
Dates: |
|
||||
Institution: | The University of York | ||||
Academic Units: | The University of York > Faculty of Sciences (York) > Physics (York) | ||||
Funding Information: |
|
||||
Depositing User: | Pure (York) | ||||
Date Deposited: | 10 Nov 2023 09:30 | ||||
Last Modified: | 30 Jan 2024 23:40 | ||||
Published Version: | https://doi.org/10.1063/5.0155621 | ||||
Status: | Published | ||||
Refereed: | Yes | ||||
Identification Number: | https://doi.org/10.1063/5.0155621 |
Download
Filename: 044803_1_5.0155621.pdf
Description: Machine-learned acceleration for molecular dynamics in CASTEP
Licence: CC-BY 2.5