High-Dimensional Potential Energy Surfaces for Molecular Simulations

Abstract

An overview of computational methods to describe high-dimensional potential energy surfaces suitable for atomistic simulations is given. Particular emphasis is put on accuracy, computability, transferability and extensibility of the methods discussed. They include empirical force fields, representations based on reproducing kernels, using permutationally invariant polynomials, and neural network-learned representations and combinations thereof. Future directions and potential improvements are discussed primarily from a practical, application-oriented perspective.

References in corpus (22)

• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Kernel methods in machine learning
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning prediction errors better than DFT accuracy
• On-the-fly machine learning force field generation: Application to melting points
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Alchemical and structural distribution based representation for improved QML
• Hierarchical modeling of molecular energies using a deep neural network
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• How large should the QM region be in QM/MM calculations? The case of catechol O-methyltransferase
• Specific chemical reactivities of spatially separated 3-aminophenol conformers with cold Ca${}^{+}$ ions
• Operators in Machine Learning: Response Properties in Chemical Space
• Direct calculation of the solid-liquid Gibbs free energy difference in a single equilibrium simulation
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Reactive Atomistic Simulations of Diels-Alder Reactions: the Importance of Molecular Rotations

Cited by in corpus (11)

• Machine Learning Force Fields
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Perspective on integrating machine learning into computational chemistry and materials science
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Graph Neural Networks Accelerated Molecular Dynamics
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Impact of the characteristics of quantum chemical databases on machine learning predictions of tautomerization energies
• Quantum neural networks force fields generation
• Stress and heat flux via automatic differentiation
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust