Incorporating long-range physics in atomic-scale machine learning

Abstract

The most successful and popular machine learning models of atomic-scale properties derive their transferability from a locality ansatz. The properties of a large molecule or a bulk material are written as a sum over contributions that depend on the configurations within finite atom-centered environments. The obvious downside of this approach is that it cannot capture non-local, non-additive effects such as those arising due to long-range electrostatics or quantum interference. We propose a solution to this problem by introducing non-local representations of the system that are remapped as feature vectors that are defined locally and are equivariant in O(3). We consider in particular one form that has the same asymptotic behavior as the electrostatic potential. We demonstrate that this framework can capture non-local, long-range physics by building a model for the electrostatic energy of randomly distributed point-charges, for the unrelaxed binding curves of charged organic molecular dimers, and for the electronic dielectric response of liquid water. By combining a representation of the system that is sensitive to long-range correlations with the transferability of an atom-centered additive model, this method outperforms current state-of-the-art machine-learning schemes, and provides a conceptual framework to incorporate non-local physics into atomistic machine learning.

References in corpus (19)

• 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
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Nearsightedness of Electronic Matter
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Atom-Density Representations for Machine Learning
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Efficient nonparametric $n$-body force fields from machine learning
• Transferable atomic multipole machine learning models for small organic molecules
• Wavelet Scattering Regression of Quantum Chemical Energies

Cited by in corpus (55)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• A deep potential model with long-range electrostatic interactions
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Deep Potentials for Materials Science
• On the Completeness of Atomic Structure Representations
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• A complete description of thermodynamic stabilities of molecular crystals
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Dielectric response with short-ranged electrostatics
• 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
• Multilayer atomic cluster expansion for semi-local interactions
• Predicting the Charge Density Response in Metal Electrodes
• Scalable neural networks for the efficient learning of disordered quantum systems
• Fast and flexible long-range models for atomistic machine learning
• Machine learning density functionals from the random-phase approximation
• 3DReact: Geometric deep learning for chemical reactions
• Machine-Learning Interatomic Potentials for Long-Range Systems
• SPA${}^{\mathrm{H}}$M: the Spectrum of Approximated Hamiltonian Matrices representations
• Accelerating QM/MM simulations of electrochemical interfaces through machine learning of electronic charge densities
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Mean-Field Density Matrix Decompositions
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Prediction rigidities for data-driven chemistry
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• Machine learning potentials for complex aqueous systems made simple
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• Shifting computational boundaries for complex organic materials
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• Learning intermolecular forces at liquid-vapor interfaces
• Learning the Electrostatic Response of the Electron Density through a Symmetry-Adapted Vector Field Model
• Efficient Long-Range Convolutions for Point Clouds
• General Learning of the Electric Response of Inorganic Materials
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Simulations of water and hydrophobic hydration using a neural network potential
• Graph Convolutional Neural Networks for (QM)ML/MM Molecular Dynamics Simulations
• Macro-Dipole-Constrainted Learning of Atomic Charges for Accurate Electrostatic Potentials at Electrochemical Interfaces
• Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
• Learning electron densities in the condensed phase