A deep potential model with long-range electrostatic interactions

Abstract

Machine learning models for the potential energy of multi-atomic systems, such as the deep potential (DP) model, make possible molecular simulations with the accuracy of quantum mechanical density functional theory, at a cost only moderately higher than that of empirical force fields. However, the majority of these models lack explicit long-range interactions and fail to describe properties that derive from the Coulombic tail of the forces. To overcome this limitation we extend the DP model by approximating the long-range electrostatic interaction between ions (nuclei+core electrons) and valence electrons with that of distributions of spherical Gaussian charges located at ionic and electronic sites. The latter are rigorously defined in terms of the centers of the maximally localized Wannier distributions, whose dependence on the local atomic environment is modeled accurately by a deep neural network. In the deep potential long-range (DPLR) model, the electrostatic energy of the Gaussian charge system is added to short-range interactions that are represented as in the standard DP model. The resulting potential energy surface is smooth and possesses analytical forces and virial. Missing effects in the standard DP scheme are recovered, improving on accuracy and predictive power. By including long-range electrostatics, DPLR correctly extrapolates to large systems the potential energy surface learned from quantum mechanical calculations on smaller systems. We illustrate the approach with three examples, the potential energy profile of the water dimer, the free energy of interaction of a water molecule with a liquid water slab, and the phonon dispersion curves of the NaCl crystal.

References in corpus (38)

• Adam: A Method for Stochastic Optimization
• Phonons and related properties of extended systems from density-functional perturbation theory
• Maximally localized Wannier functions: Theory and applications
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• 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
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Nearsightedness of Electronic Matter
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Molecular Dynamics Simulations of Lipid Bilayers: Major Artifacts due to Truncating Electrostatic Interactions
• The Phase Diagram of a Deep Potential Water Model
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Neural Network Based in Silico Simulation of Combustion Reactions
• Hierarchical modeling of molecular energies using a deep neural network
• Deep Potential: a general representation of a many-body potential energy surface
• 86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy
• Incorporating long-range physics in atomic-scale machine learning
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Deep neural network for the dielectric response of insulators
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Molecular Simulation of Electrode-Solution Interfaces
• Transferable atomic multipole machine learning models for small organic molecules
• Role of dipolar correlations in the IR spectra of water and ice
• Structure and dielectric properties of polar fluids with extended dipoles: results from numerical simulations
• Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning

Cited by in corpus (32)

• DeePMD-kit v2: A software package for Deep Potential models
• A practical guide to machine learning interatomic potentials -- Status and future
• Homogeneous ice nucleation in an ab initio machine learning model of water
• Tutorial: How to Train a Neural Network Potential
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• A first-principles machine-learning force field for heterogeneous ice nucleation on microcline feldspar
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Predicting the Charge Density Response in Metal Electrodes
• Towards fully ab initio simulation of atmospheric aerosol nucleation
• Fast and flexible long-range models for atomistic machine learning
• Finite-temperature properties of antiferroelectric perovskite $\mathrm{PbZr}{\mathrm{O}}_3$ from deep learning interatomic potential
• Machine-Learning Interatomic Potentials for Long-Range Systems
• Large-scale Atomistic Simulation of Quantum Effects in SrTiO${}_3$ from First Principles
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• A chemical bond-based machine learning model for dipole moment: Application to dielectric properties of liquid methanol and ethanol
• Thermal disorder and phonon softening in the ferroelectric phase transition of lead titanate
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Role of long-range dipolar interactions in the simulation of the properties of polar crystals using effective atomic potentials
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Consistency between the Green-Kubo formula and Lorentz model for predicting the infrared dielectric function of polar materials
• Pressure-Induced Structural and Dielectric Changes in Liquid Water at Room Temperature
• Transferability of the chemical bond-based machine learning model for dipole moment: the GHz to THz dielectric properties of liquid propylene glycol and polypropylene glycol
• General Learning of the Electric Response of Inorganic Materials
• A unified machine-learning framework for ab initio multiscale modeling of liquids
• Macro-Dipole-Constrainted Learning of Atomic Charges for Accurate Electrostatic Potentials at Electrochemical Interfaces