Adaptive coupling of a deep neural network potential to a classical force field

Abstract

An adaptive modeling method (AMM) that couples a deep neural network potential and a classical force field is introduced to address the accuracy-efficiency dilemma faced by the molecular simulation community. The AMM simulated system is decomposed into three types of regions. The first type captures the important phenomena in the system and requires high accuracy, for which we use the Deep Potential Molecular Dynamics (DeePMD) model in this work. The DeePMD model is trained to accurately reproduce the statistical properties of the ab initio molecular dynamics. The second type does not require high accuracy and a classical force field is used to describe it in an efficient way. The third type is used for a smooth transition between the first and the second types of regions. By using a force interpolation scheme and imposing a thermodynamics force in the transition region, we make the DeePMD region embedded in the AMM simulated system as if it were embedded in a system that is fully described by the accurate potential. A representative example of the liquid water system is used to show the feasibility and promise of this method.

References in corpus (20)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• How van der Waals interactions determine the unique properties of water
• Adaptive Resolution Molecular Dynamics Simulation: Changing the Degrees of Freedom on the Fly
• Deep Potential: a general representation of a many-body potential energy surface
• Adaptive resolution molecular dynamics simulation through coupling to an internal particle reservoir
• Grand-canonical-like molecular-dynamics simulations by using an adaptive-resolution technique
• Some fundamental problems for an energy conserving adaptive resolution molecular dynamics scheme
• Classical-path integral adaptive resolution in molecular simulation: towards a smooth quantum-classical coupling
• Molecular Dynamics in a Grand Ensemble: Bergmann-Lebowitz model and Adaptive Resolution Simulation
• Path Integral Molecular Dynamics within the Grand Canonical-like Adaptive Resolution Technique: Simulation of Liquid Water
• Theory-based Benchmarking of the Blended Force-Based Quasicontinuum Method
• Formulation of Liouville's Theorem for Grand Ensemble Molecular Simulations
• Sampling the isothermal-isobaric ensemble by Langevin dynamics
• Adaptive Resolution Simulation in Equilibrium and Beyond

Cited by in corpus (4)

• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• Local structure, thermodynamics, and melting curve of boron phosphide at high pressures by deep learning-driven ab initio simulations
• Adaptive-precision potentials for large-scale atomistic simulations
• Nanoindentation simulations for copper and tungsten with adaptive-precision potentials