Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network

Abstract

Based on an analysis of the short range chemical environment of each atom in a system, standard machine learning based approaches to the construction of interatomic potentials aim at determining directly the central quantity which is the total energy. This prevents for instance an accurate description of the energetics of systems where long range charge transfer is important as well as of ionized systems. We propose therefore not to target directly with machine learning methods the total energy but an intermediate physical quantity namely the charge density, which then in turn allows to determine the total energy. By allowing the electronic charge to distribute itself in an optimal way over the system, we can describe not only neutral but also ionized systems with unprecedented accuracy. We demonstrate the power of our approach for both neutral and ionized NaCl clusters where charge redistribution plays a decisive role for the energetics. We are able to obtain chemical accuracy, i.e. errors of less than a milli Hartree per atom compared to the reference density functional results. The introduction of physically motivated quantities which are determined by the short range atomic environment via a neural network leads also to an increased stability of the machine learning process and transferability of the potential.

4 figures

References in corpus (1)

• Efficient solution of Poisson's equation with free boundary conditions

Cited by in corpus (62)

• Machine Learning Force Fields
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Comparing molecules and solids across structural and alchemical space
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• A Transferable Machine-Learning Model of the Electron Density
• A deep potential model with long-range electrostatic interactions
• Incorporating long-range physics in atomic-scale machine learning
• Deep Potentials for Materials Science
• Committee neural network potentials control generalization errors and enable active learning
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Challenges in Large Scale Quantum Mechanical Calculations
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• The Many-Body Expansion Combined with Neural Networks
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• Stratified construction of neural network based interatomic models for multicomponent materials
• Tutorial: How to Train a Neural Network Potential
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Insights into lithium manganese oxide-water interfaces using machine learning potentials
• Conceptual and practical bases for the high accuracy of machine learning interatomic potential
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Lifelong Machine Learning Potentials
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Infrared spectra at coupled cluster accuracy from neural network representations
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• Exploring a potential energy surface by machine learning for characterizing atomic transport
• Explicitly correlated double hybrid DFT: a comprehensive analysis of the basis set convergence on the GMTKN55 database
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• Predicting the Charge Density Response in Metal Electrodes
• FLAME: a library of atomistic modeling environments
• Genarris: Random Generation of Molecular Crystal Structures and Fast Screening with a Harris Approximation
• Modeling electronic response properties with an explicit-electron machine learning potential
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• Linearized machine-learning interatomic potentials for non-magnetic elemental metals: Limitation of pairwise descriptors and trend of predictive power
• Accelerating fourth-generation machine learning potentials by quasi-linear scaling particle mesh charge equilibration
• Accuracy of Charge Densities in Electronic Structure Calculations
• Thermal conductivity of CaF${}_2$ at high pressure
• How Graph Neural Network Interatomic Potentials Extrapolate: Role of the Message-Passing Algorithm
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Large Scale Structure Prediction of Near-Stoichiometric Magnesium Oxide Based on a Machine-Learned Interatomic Potential: Novel Crystalline Phases and Oxygen-Vacancy Ordering
• Shadow molecular dynamics and atomic cluster expansions for flexible charge models
• Machine learning potentials for complex aqueous systems made simple
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• Embedding quantum statistical excitations in a classical force field
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
• Ab initio machine learning in chemical compound space
• Teaching oxidation states to neural networks
• Machine-Learned Potentials for Solvation Modeling
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials