Machine Learning Force Fields

Abstract

In recent years, the use of Machine Learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.

References in corpus (34)

• Deep Learning in Neural Networks: An Overview
• Practical Bayesian Optimization of Machine Learning Algorithms
• ADADELTA: An Adaptive Learning Rate Method
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Kernel methods in machine learning
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Machine learning for molecular simulation
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• How van der Waals interactions determine the unique properties of water
• Machine learning for electronically excited states of molecules
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
• Reactive Dynamics and Spectroscopy of Hydrogen Transfer from Neural Network-Based Reactive Potential Energy Surfaces
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• The optimal assignment kernel is not positive definite
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Converged Colored Noise Path Integral Molecular Dynamics Study of the Zundel Cation down to Ultra-low Temperatures at Coupled Cluster Accuracy
• Generating valid Euclidean distance matrices
• Isomerization and Decomposition Reactions of Acetaldehyde Relevant to Atmospheric Processes from Dynamics Simulations on Neural Network-Based Potential Energy Surfaces
• Reinforcement Learning for Molecular Design Guided by Quantum Mechanics
• Thermal Activation of Methane by MgO${}^{+}$: Temperature Dependent Kinetics, Reactive Molecular Dynamics Simulations and Statistical Modeling
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights

Cited by in corpus (67)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Physics-inspired structural representations for molecules and materials
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• SELFIES and the future of molecular string representations
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Deep Potentials for Materials Science
• Inverse design of 3d molecular structures with conditional generative neural networks
• Perspective on integrating machine learning into computational chemistry and materials science
• Quantum Machine Learning for Chemistry and Physics
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Ab-initio quantum chemistry with neural-network wavefunctions
• How to validate machine-learned interatomic potentials
• Unified Graph Neural Network Force-field for the Periodic Table
• Toward Explainable AI for Regression Models
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Atomic-scale origin of the low grain-boundary resistance in perovskite solid electrolytes
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Ultra-fast interpretable machine-learning potentials
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Machine Learning Directed Optimization of Classical Molecular Modeling Force Fields
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Deep-learning electronic-structure calculation of magnetic superstructures
• Universal QM/MM Approaches for General Nanoscale Applications
• Frontiers, challenges, and solutions in modeling of swift heavy ion effects in materials
• Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
• 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
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Predicting the failure of two-dimensional silica glasses
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
• Incorporating Nuclear Quantum Effects in Molecular Dynamics with a Constrained Minimized Energy Surface
• Learning Pair Potentials using Differentiable Simulations
• Towards fully ab initio simulation of atmospheric aerosol nucleation
• Neural network with optimal neuron activation functions based on additive Gaussian process regression
• Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics
• Thirty years of molecular dynamics simulations on posttranslational modifications of proteins
• Modeling electronic response properties with an explicit-electron machine learning potential
• Impact of the characteristics of quantum chemical databases on machine learning predictions of tautomerization energies
• Innate Dynamics and Identity Crisis of a Metal Surface Unveiled by Machine Learning of Atomic Environments
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• Quantum neural networks force fields generation
• Reliable emulation of complex functionals by active learning with error control
• Accelerating discrete dislocation dynamics simulations with graph neural networks
• SPA${}^{\mathrm{H}}$M: the Spectrum of Approximated Hamiltonian Matrices representations
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Decomposing Chemical Space: Applications to the Machine Learning of Atomic Energies
• The prospects of Monte Carlo antibody loop modelling on a fault-tolerant quantum computer
• Mean-Field Density Matrix Decompositions
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• High-Throughput Condensed-Phase Hybrid Density Functional Theory for Large-Scale Finite-Gap Systems: The SeA Approach
• Extending the reach of quantum computing for materials science with machine learning potentials
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
• Machine learning frontier orbital energies of nanodiamonds
• Symbolic Regression in Materials Science: Discovering Interatomic Potentials from Data
• Ab initio machine learning in chemical compound space
• Transfer Learned Potential Energy Surfaces: Accurate Anharmonic Vibrational Dynamics and Dissociation Energies for the Formic Acid Monomer and Dimer
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• Self-supervised Representations and Node Embedding Graph Neural Networks for Accurate and Multi-scale Analysis of Materials
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Quantitative Molecular Simulations