Kernel-Based Machine Learning for Efficient Simulations of Molecular Liquids
Open Access
- 13 April 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 16 (5) , 3194-3204
Abstract
Current machine learning (ML) models aimed at learning force fields are plagued by their high computational cost at every integration time step. We describe a number of practical and computationally-efficient strategies to parametrize traditional force fields for molecular liquids from ML: the particle decomposition ansatz to two- and three-body force fields, the use of kernel-based ML models that incorporate physical symmetries, the incorporation of switching functions close to the cutoff, and the use of covariant meshing to boost the training set size. Results are presented for model molecular liquids: pairwise Lennard-Jones, three-body Stillinger-Weber, and bottom-up coarse-graining of water. Here, covariant meshing proves to be an efficient strategy to learn canonically averaged instantaneous forces. We show that molecular dynamics simulations with tabulated two- and three-body ML potentials are computationally efficient and recover two- and three-body distribution functions. Many-body representations, decomposition, and kernel regression schemes are all implemented in the open-source software package VOTCA.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (TRR 146)
- Institute for Pure and Applied Mathematics
This publication has 43 references indexed in Scilit:
- Data-Driven Learning of Total and Local Energies in Elemental BoronPhysical Review Letters, 2018
- Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansionsThe Journal of Chemical Physics, 2018
- Machine learning of accurate energy-conserving molecular force fieldsScience Advances, 2017
- Machine learning based interatomic potential for amorphous carbonPhysical Review B, 2017
- Exploration, Sampling, And Reconstruction of Free Energy Surfaces with Gaussian Process RegressionJournal of Chemical Theory and Computation, 2016
- Gaussian approximation potentials: A brief tutorial introductionInternational Journal of Quantum Chemistry, 2015
- “Learn on the Fly”: A Hybrid Classical and Quantum-Mechanical Molecular Dynamics SimulationPhysical Review Letters, 2004
- Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networksChemical Physics Letters, 2004
- A general method for constructing multidimensional molecular potential energy surfaces from ab initio calculationsThe Journal of Chemical Physics, 1996
- Potential energy surfaces for macromolecules. A neural network techniqueChemical Physics Letters, 1992