Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions

Abstract

The accurate representation of multidimensional potential energy surfaces is a necessary requirement for realistic computer simulations of molecular systems. The continued increase in computer power accompanied by advances in correlated electronic structure methods nowadays enable routine calculations of accurate interaction energies for small systems, which can then be used as references for the development of analytical potential energy functions (PEFs) rigorously derived from many-body expansions. Building on the accuracy of the MB-pol many-body PEF, we investigate here the performance of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water two-body and three-body interaction energies, denoting the resulting potentials PIP-MB-pol, BPNN-MB-pol, and GAP-MB-pol, respectively. Our analysis shows that all three analytical representations exhibit similar levels of accuracy in reproducing both two-body and three-body reference data as well as interaction energies of small water clusters obtained from calculations carried out at the coupled cluster level of theory, the current gold standard for chemical accuracy. These results demonstrate the synergy between interatomic potentials formulated in terms of a many-body expansion, such as MB-pol, that are physically sound and transferable, and machine-learning techniques that provide a flexible framework to approximate the short-range interaction energy terms.

References in corpus (9)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Competing quantum effects in the dynamics of a flexible water model
• How van der Waals interactions determine the unique properties of water
• On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice
• The Many-Body Expansion Combined with Neural Networks
• On the representation of many-body interactions in water

Cited by in corpus (38)

• Machine learning and the physical sciences
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Physics-inspired structural representations for molecules and materials
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Automated discovery of a robust interatomic potential for aluminum
• Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
• Efficient implementation of atom-density representations
• Accelerating Atomistic Simulations with Piecewise Machine Learned Ab Initio Potentials at Classical Force Field-like Cost
• ML Models of Vibrating H${}_2$CO: Comparing Reproducing Kernels, FCHL and PhysNet
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
• A comparative study of different machine learning methods for dissipative quantum dynamics
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• Nuclear-Electronic All-Particle Density Matrix Renormalization Group
• Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
• A $\Delta$-Machine Learning Approach for Force Fields, Illustrated by a CCSD(T) 4-body Correction to the MB-pol Water Potential
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• Constructing and evaluating machine-learned interatomic potentials for Li-based disordered rocksalts
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• Machine-learning of atomic-scale properties based on physical principles
• Tunneling splittings of vibrationally excited states using general instanton paths
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Aqueous Solution Chemistry In Silico and the Role of Data Driven Approaches
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Symmetry- and Gradient-enhanced Gaussian Process Regression for the Active Learning of Potential Energy Surfaces in Porous Materials
• Analogy between Boltzmann machines and Feynman path integrals