Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields

Abstract

Molecular dynamics (MD) simulations employing classical force fields constitute the cornerstone of contemporary atomistic modeling in chemistry, biology, and materials science. However, the predictive power of these simulations is only as good as the underlying interatomic potential. Classical potentials often fail to faithfully capture key quantum effects in molecules and materials. Here we enable the direct construction of flexible molecular force fields from high-level ab initio calculations by incorporating spatial and temporal physical symmetries into a gradient-domain machine learning (sGDML) model in an automatic data-driven way. The developed sGDML approach faithfully reproduces global force fields at quantum-chemical CCSD(T) level of accuracy and allows converged molecular dynamics simulations with fully quantized electrons and nuclei. We present MD simulations, for flexible molecules with up to a few dozen atoms and provide insights into the dynamical behavior of these molecules. Our approach provides the key missing ingredient for achieving spectroscopic accuracy in molecular simulations.

References in corpus (13)

• Machine Learning Unifies the Modelling of Materials and Molecules
• VAMPnets: Deep learning of molecular kinetics
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Hierarchical modeling of molecular energies using a deep neural network
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Efficient nonparametric $n$-body force fields from machine learning
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• High-dimensional neural network potentials for solvation: The case of protonated water clusters in helium
• Exploring a potential energy surface by machine learning for characterizing atomic transport
• An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields

Cited by in corpus (167)

• Machine learning and the physical sciences
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Machine Learning Force Fields
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Machine learning for molecular simulation
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Towards Explainable Artificial Intelligence
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Machine learning for electronically excited states of molecules
• FCHL revisited: faster and more accurate quantum machine learning
• Physically-informed artificial neural networks for atomistic modeling of materials
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• A deep potential model with long-range electrostatic interactions
• De novo exploration and self-guided learning of potential-energy surfaces
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Machine learning enables long time scale molecular photodynamics simulations
• Perspective on integrating machine learning into computational chemistry and materials science
• Inverse design of 3d molecular structures with conditional generative neural networks
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• $\Delta$-Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Unified Graph Neural Network Force-field for the Periodic Table
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy
• Uncertainty estimation for molecular dynamics and sampling
• Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Sparse Gaussian Process Potentials: Application to Lithium Diffusivity in Superionic Conducting Solid Electrolytes
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• A complete description of thermodynamic stabilities of molecular crystals
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Machine Learning Implicit Solvation for Molecular Dynamics
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• AI-driven inverse design of materials: Past, present and future
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• Neural networks and kernel ridge regression for excited states dynamics of CH${}_2$NH${}_2^{+}$: From single-state to multi-state representations and multi-property machine learning models
• Building and Interpreting Deep Similarity Models
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Machine learning and excited-state molecular dynamics
• Graph Neural Networks Accelerated Molecular Dynamics
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• 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
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Spin-Dependent Graph Neural Network Potential for Magnetic Materials
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Efficient implementation of atom-density representations
• Optimization and Validation of a Deep Learning CuZr Atomistic Potential: Robust Applications for Crystalline and Amorphous Phases with near-DFT Accuracy
• Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects
• Transfer learning for chemically accurate interatomic neural network potentials
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Machine learning for molecular dynamics with strongly correlated electrons
• Atomic energy mapping of neural network potential
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Automated construction of quantum-classical hybrid models
• Converged Colored Noise Path Integral Molecular Dynamics Study of the Zundel Cation down to Ultra-low Temperatures at Coupled Cluster Accuracy
• Self-Parametrizing System-Focused Atomistic Models
• Modeling nanoconfinement effects using active learning
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• Piezoelectric modulus prediction using machine learning and graph neural networks
• MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
• Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Moments
• An Extendible, Graph-Neural-Network-Based Approach for Accurate Force Field Development of Large Flexible Organic Molecules
• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Modeling electronic response properties with an explicit-electron machine learning potential
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Nucleating a Different Coordination in a Crystal under Pressure: A Study of the B1-B2 Transition in NaCl by Metadynamics
• Efficacy of the Radial Pair Potential Approximation for Molecular Dynamics Simulations of Dense Plasmas
• $\Delta$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
• Reliable emulation of complex functionals by active learning with error control
• Kernel based quantum machine learning at record rate : Many-body distribution functionals as compact representations
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Uncertainty quantification and estimation in differential dynamic microscopy
• Modeling intermolecular and intramolecular modes of liquid water using multiple heat baths: Machine learning approach
• 3DReact: Geometric deep learning for chemical reactions
• Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
• Energy-conserving molecular dynamics is not energy conserving
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Accurate quantum Monte Carlo forces for machine-learned force fields: Ethanol as a benchmark
• Stress and heat flux via automatic differentiation
• A complete OSV-MP2 analytical gradient theory for molecular structure and dynamics simulations
• Molecular Quantum Chemical Data Sets and Databases for Machine Learning Potentials
• Wasserstein metric for improved QML with adjacency matrix representations
• Quantum calculations on a new CCSD(T) machine-learned PES reveal the leaky nature of gas-phase $trans$ and $gauche$ ethanol conformers
• GPU-Accelerated Approximate Kernel Method for Quantum Machine Learning
• Machine learning for phase ordering dynamics of charge density waves
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• Analytical Gradients for Molecular-Orbital-Based Machine Learning
• Decomposing Chemical Space: Applications to the Machine Learning of Atomic Energies
• Tutorial: AI-assisted exploration and active design of polymers with high intrinsic thermal conductivity
• Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
• No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
• Augmentation of Universal Potentials for Broad Applications
• Mean-Field Density Matrix Decompositions
• Learning on-top: regressing the on-top pair density for real-space visualization of electron correlation
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Accelerated calculation of configurational free energy using a combination of reverse Monte Carlo and neural network models: Adsorption isotherm for 2D square and triangular lattices
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• A Unified Theory of Free Energy Functionals and Applications to Diffusion
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
• Shifting computational boundaries for complex organic materials
• A Fully Quantum-Mechanical Treatment for Kaolinite
• Neural-networks model for force prediction in multi-principal-element alloys
• Scaling Graph Neural Networks to Large Proteins
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations
• Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Symmetry- and Gradient-enhanced Gaussian Process Regression for the Active Learning of Potential Energy Surfaces in Porous Materials
• Machine-learning interatomic potentials achieving CCSD(T) accuracy for systems with extended covalent networks and van der Waals interactions
• Generation of ultrashort ion pulses from ultrafast electron-stimulated desorption
• A Data-Driven Approach to Coarse-Graining Simple Liquids in Confinement
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Reactive atomistic simulations of Diels-Alder-type reactions: Conformational and dynamic effects in the polar cycloaddition of 2,3-dibromobutadiene radical ions with maleic anhydride
• On Simulating Thin-Film Processes at the Atomic Scale Using Machine Learned Force Fields
• Error Bounds of the Invariant Statistics in Machine Learning of Ergodic Itô Diffusions
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Space
• Enhancing ab initio diffusion calculations in materials through Gaussian process regression
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• Machine-learning force-field models for dynamical simulations of metallic magnets
• Kinetically Arrested Twin-Domain State in Formamidinium Lead Iodide
• Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model
• Interpretable, Physics-Informed Learning Reveals Sulfur Adsorption and Poisoning Mechanisms in 13-Atom Icosahedra Nanoclusters
• Uncertainty in AI-driven Monte Carlo simulations
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning
• Machine learning approach for vibronically renormalized electronic band structures
• Active Learning of a Neural Network Potential for Large-Scale Atomistic Simulations of Polymer Electrolyte Membranes
• On the forbidden graphene's ZO (out-of-plane optic) phononic band-analog vibrational modes in fullerenes
• Quantitative Molecular Simulations
• Fast Evaluation of Unbiased Atomic Forces in ab initio Variational Monte Carlo via the Lagrangian Technique