Efficient machine-learning based interatomic potentialsfor exploring thermal conductivity in two-dimensional materials

verfasst von

Bohayra Mortazavi, Evgeny V. Podryabinkin, Ivan S Novikov, Stephan Roche, Timon Rabczuk, Xiaoying Zhuang, Alexander V. Shapeev

Abstract

It is well-known that the calculation of thermal conductivity using classical molecular dynamics (MD) simulations strongly depends on the choice of the appropriate interatomic potentials. As proven for the case of graphene, while most of the available interatomic potentials estimate the structural and elastic constants with high accuracy, when employed to predict the lattice thermal conductivity they however lead to a variation of predictions by one order of magnitude. Here we present our results on using machine-learning interatomic potentials (MLIPs) passively fitted to computationally inexpensive ab-initio molecular dynamics trajectories without any tuning or optimizing of hyperparameters. These first-attempt potentials could reproduce the phononic properties of different two-dimensional (2D) materials obtained using density functional theory (DFT) simulations. To illustrate the efficiency of the trained MLIPs, we consider polyaniline C

₃N nanosheets. C

₃N monolayer was selected because the classical MD and different first-principles results contradict each other, resulting in a scientific dilemma. It is shown that the predicted thermal conductivity of 418 ± 20 W mK

⁻

¹ for C

₃N monolayer by the non-equilibrium MD simulations on the basis of a first-attempt MLIP evidences an improved accuracy when compared with the commonly employed MD models. Moreover, MLIP-based prediction can be considered as a solution to the debated reports in the literature. This study highlights that passively fitted MLIPs can be effectively employed as versatile and efficient tools to obtain accurate estimations of thermal conductivities of complex materials using classical MD simulations. In response to remarkable growth of 2D materials family, the devised modeling methodology could play a fundamental role to predict the thermal conductivity.

Organisationseinheit(en)

Institut für Kontinuumsmechanik

Externe Organisation(en)

Institució Catalana de Recerca i Estudis Avançats (ICREA)
Tongji University
Skolkovo Innovation Center
Universidad Autónoma de Barcelona (UAB)

Typ

Artikel

Journal

Journal of Physics: Materials

Band

Seiten

02LT02

Publikationsdatum

09.04.2020

Publikationsstatus

Veröffentlicht

ASJC Scopus Sachgebiete

Physik der kondensierten Materie, Atom- und Molekularphysik sowie Optik, Werkstoffwissenschaften (insg.)

Elektronische Version(en)

https://doi.org/10.1088/2515-7639/ab7cbb (Zugang: Offen)

Details im Forschungsportal „Research@Leibniz University“

BibTeX

@article{ff0e92c93ce04afca3977441d3195ae8,
title = "Efficient machine-learning based interatomic potentialsfor exploring thermal conductivity in two-dimensional materials",
abstract = "It is well-known that the calculation of thermal conductivity using classical molecular dynamics (MD) simulations strongly depends on the choice of the appropriate interatomic potentials. As proven for the case of graphene, while most of the available interatomic potentials estimate the structural and elastic constants with high accuracy, when employed to predict the lattice thermal conductivity they however lead to a variation of predictions by one order of magnitude. Here we present our results on using machine-learning interatomic potentials (MLIPs) passively fitted to computationally inexpensive ab-initio molecular dynamics trajectories without any tuning or optimizing of hyperparameters. These first-attempt potentials could reproduce the phononic properties of different two-dimensional (2D) materials obtained using density functional theory (DFT) simulations. To illustrate the efficiency of the trained MLIPs, we consider polyaniline C 3N nanosheets. C 3N monolayer was selected because the classical MD and different first-principles results contradict each other, resulting in a scientific dilemma. It is shown that the predicted thermal conductivity of 418 ± 20 W mK − 1 for C 3N monolayer by the non-equilibrium MD simulations on the basis of a first-attempt MLIP evidences an improved accuracy when compared with the commonly employed MD models. Moreover, MLIP-based prediction can be considered as a solution to the debated reports in the literature. This study highlights that passively fitted MLIPs can be effectively employed as versatile and efficient tools to obtain accurate estimations of thermal conductivities of complex materials using classical MD simulations. In response to remarkable growth of 2D materials family, the devised modeling methodology could play a fundamental role to predict the thermal conductivity. ",
keywords = "Density functional theory simulations, Machine learning, Molecular dynamics, Thermal conductivity, Two-dimensional polyaniline C3N monolayer",
author = "Bohayra Mortazavi and Podryabinkin, {Evgeny V.} and Novikov, {Ivan S} and Stephan Roche and Timon Rabczuk and Xiaoying Zhuang and Shapeev, {Alexander V.}",
note = "Publisher Copyright: {\textcopyright} 2020 The Author(s). Published by IOP Publishing Ltd. ",
year = "2020",
month = apr,
day = "9",
doi = "10.1088/2515-7639/ab7cbb",
language = "English",
volume = "3",
pages = "02LT02",
journal = "Journal of Physics: Materials",
issn = "2515-7639",
publisher = "IOP Publishing Ltd.",
number = "2",
}