SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects

Abstract

Machine-learned force fields (ML-FFs) combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current ML-FFs typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing ML-FFs with explicit treatment of electronic degrees of freedom and quantum nonlocality. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today's machine learning models in quantum chemistry.

References in corpus (51)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Neural Message Passing for Quantum Chemistry
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Gaussian Error Linear Units (GELUs)
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• On the Convergence of Adam and Beyond
• Machine Learning Force Fields
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Machine Learning Unifies the Modelling of Materials and Molecules
• Searching for Activation Functions
• Resolution-of-identity approach to Hartree-Fock, hybrid density functionals, RPA, MP2, and \textit{GW} with numeric atom-centered orbital basis functions
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Highway Networks
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Directional Message Passing for Molecular Graphs
• FCHL revisited: faster and more accurate quantum machine learning
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Hierarchical modeling of molecular energies using a deep neural network
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Equivariant message passing for the prediction of tensorial properties and molecular spectra
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Incorporating long-range physics in atomic-scale machine learning
• On the Completeness of Atomic Structure Representations
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Cormorant: Covariant Molecular Neural Networks
• The Expressive Power of Neural Networks: A View from the Width
• Rethinking Attention with Performers
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Charge separation in donor-C60 complexes with real-time Green's functions: The importance of nonlocal correlations
• Large yet bounded: Spin gap ranges in carbenes
• Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networks

Cited by in corpus (64)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Machine Learning Coarse-Grained Potentials of Protein Thermodynamics
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Toward Explainable AI for Regression Models
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Graph Neural Networks Accelerated Molecular Dynamics
• Deep-learning electronic-structure calculation of magnetic superstructures
• Deep-learning density functional perturbation theory
• TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Lifelong Machine Learning Potentials
• Molecular dynamics simulation with finite electric fields using Perturbed Neural Network Potentials
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• On the design space between molecular mechanics and machine learning force fields
• Neural network with optimal neuron activation functions based on additive Gaussian process regression
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Modeling electronic response properties with an explicit-electron machine learning potential
• Lightweight and Effective Tensor Sensitivity for Atomistic Neural Networks
• Heat flux for semi-local machine-learning potentials
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Reinforcement learning for traversing chemical structure space: Optimizing transition states and minimum energy paths of molecules
• Fast and flexible long-range models for atomistic machine learning
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution
• 3DReact: Geometric deep learning for chemical reactions
• Machine-Learning Interatomic Potentials for Long-Range Systems
• Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
• Machine Learning for Exploring Small Polaron Configurational Space
• Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems
• Accurate quantum Monte Carlo forces for machine-learned force fields: Ethanol as a benchmark
• Stress and heat flux via automatic differentiation
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• How Graph Neural Network Interatomic Potentials Extrapolate: Role of the Message-Passing Algorithm
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Scaling Molecular Dynamics with ab initio Accuracy to 149 Nanoseconds per Day
• Molecular relaxation by reverse diffusion with time step prediction
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• A Data-Driven Approach to Coarse-Graining Simple Liquids in Confinement
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
• Machine-Learned Potentials for Solvation Modeling
• Probing the Temporal Response of Liquid Water to a THz Pump Pulse Using Machine Learning-Accelerated Non-Equilibrium Molecular Dynamics
• Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
• Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
• Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks
• Graph Convolutional Neural Networks for (QM)ML/MM Molecular Dynamics Simulations
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Active Learning of a Neural Network Potential for Large-Scale Atomistic Simulations of Polymer Electrolyte Membranes