Active learning of linearly parametrized interatomic potentials

被引：429

作者：

Podryabinkin, Evgeny V. ^{[1
]}

Shapeev, Alexander V. ^{[1
]}

机构：

[1] Skolkovo Inst Sci & Technol, Moscow, Russia

来源：

COMPUTATIONAL MATERIALS SCIENCE | 2017年 / 140卷

关键词：

Interatomic potential; Active learning; Learning on the fly; Machine learning; Atomistic simulation; Moment tensor potentials; NEURAL-NETWORK POTENTIALS; TOTAL-ENERGY CALCULATIONS; MOLECULAR-DYNAMICS; SIMULATIONS; SURFACE;

D O I：

10.1016/j.commatsci.2017.08.031

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning approach is highly efficient in training potentials on the fly, ensuring that no extrapolation is attempted and leading to a completely reliable atomistic simulation without any significant decrease in accuracy. We apply our approach to molecular dynamics and structure relaxation, and we argue that it can be applied, in principle, to any other type of atomistic simulation. The software, test cases, and examples of usage are published at http://gitlab.skoltech.ru/shapeev/mlip/. (C) 2017 Elsevier B.V. All rights reserved.

引用

页码：171 / 180

页数：10

共 45 条

[1]

Artacho E, 1999, PHYS STATUS SOLIDI B, V215, P809, DOI 10.1002/(SICI)1521-3951(199909)215:1<809::AID-PSSB809>3.0.CO

[2]

2-0

[3]

Artrith N., 2015, COMP MATER SCI, V110, P20

[4] An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 [J].

Artrith, Nongnuch ;

Urban, Alexander .

COMPUTATIONAL MATERIALS SCIENCE, 2016, 114 :135-150

[5] Machine-learning approach for one- and two-body corrections to density functional theory: Applications to molecular and condensed water [J].

Bartok, Albert P. ;

Gillan, Michael J. ;

Manby, Frederick R. ;

Csanyi, Gabor .

PHYSICAL REVIEW B, 2013, 88 (05)

[6] On representing chemical environments [J].

Bartok, Albert P. ;

Kondor, Risi ;

Csanyi, Gabor .

PHYSICAL REVIEW B, 2013, 87 (18)

[7] Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons [J].

Bartok, Albert P. ;

Payne, Mike C. ;

Kondor, Risi ;

Csanyi, Gabor .

PHYSICAL REVIEW LETTERS, 2010, 104 (13)

[8] Representing potential energy surfaces by high-dimensional neural network potentials [J].

Behler, J. .

JOURNAL OF PHYSICS-CONDENSED MATTER, 2014, 26 (18)

[9] Generalized neural-network representation of high-dimensional potential-energy surfaces [J].

Behler, Joerg ;

Parrinello, Michele .

PHYSICAL REVIEW LETTERS, 2007, 98 (14)

[10] Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations [J].

Behler, Joerg .

PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2011, 13 (40) :17930-17955

← 1 2 3 4 5 →