Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials

Abstract

Machine learning has the potential to revolutionize the field of molecular simulation through the development of efficient and accurate models of interatomic interactions. In particular, neural network models can describe interactions at the level of accuracy of quantum mechanics-based calculations, but with a fraction of the cost, enabling the simulation of large systems over long timescales with ab initio accuracy. However, implicit in the construction of neural network potentials is an assumption of locality, wherein atomic arrangements on the scale of about a nanometer are used to learn interatomic interactions. Because of this assumption, the resulting neural network models cannot describe long-range interactions that play critical roles in dielectric screening and chemical reactivity. To address this issue, we introduce the self-consistent field neural network (SCFNN) model -- a general approach for learning the long-range response of molecular systems in neural network potentials. The SCFNN model relies on a physically meaningful separation of the interatomic interactions into short- and long-range components, with a separate network to handle each component. We demonstrate the success of the SCFNN approach in modeling the dielectric properties of bulk liquid water, and show that the SCFNN model accurately predicts long-range polarization correlations and the response of water to applied electrostatic fields. Importantly, because of the separation of interactions inherent in our approach, the SCFNN model can be combined with many existing approaches for building neural network potentials. Therefore, we expect the SCFNN model to facilitate the proper description of long-range interactions in a wide-variety of machine learning-based force fields.

9 pages, 4 figures, 1 table

References in corpus (11)

• Nearsightedness of Electronic Matter
• How van der Waals interactions determine the unique properties of water
• Ab initio theory and modeling of water
• The Individual and Collective Effects of Exact Exchange and Dispersion Interactions on the Ab Initio Structure of Liquid Water
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Interplay of local hydrogen-bonding and long-ranged dipolar forces in simulations of confined water
• Local molecular field theory for the treatment of electrostatics
• Stabilization of AgI's polar surfaces by the aqueous environment, and its implications for ice formation
• The Symmetry-Preserving Mean Field Condition for Electrostatic Correlations in Bulk
• Learning intermolecular forces at liquid-vapor interfaces

Cited by in corpus (25)

• A deep potential model with long-range electrostatic interactions
• A practical guide to machine learning interatomic potentials -- Status and future
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Spectroscopy from Machine Learning by Accurately Representing the Atomic Polar Tensor
• Molecular dynamics simulation with finite electric fields using Perturbed Neural Network Potentials
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Fully First-Principles Surface Spectroscopy with Machine Learning
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• Entropy governs the structure and reactivity of water dissociation under electric fields
• Predicting the Charge Density Response in Metal Electrodes
• Fast and flexible long-range models for atomistic machine learning
• Machine-Learning Interatomic Potentials for Long-Range Systems
• How Graph Neural Network Interatomic Potentials Extrapolate: Role of the Message-Passing Algorithm
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• A Fully Quantum-Mechanical Treatment for Kaolinite
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• Role of long-range dipolar interactions in the simulation of the properties of polar crystals using effective atomic potentials
• 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
• Probing the Temporal Response of Liquid Water to a THz Pump Pulse Using Machine Learning-Accelerated Non-Equilibrium Molecular Dynamics
• The Finite Coulomb Lattice Sum: A Resolution of Conditional Convergence through Exact Shape and Size
• 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