Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems

Abstract

Neural network force field (NNFF) is a method for performing regression on atomic structure-force relationships, bypassing expensive quantum mechanics calculation which prevents the execution of long ab-initio quality molecular dynamics simulations. However, most NNFF methods for complex multi-element atomic systems indirectly predict atomic force vectors by exploiting just atomic structure rotation-invariant features and the network-feature spatial derivatives which are computationally expensive. We develop a staggered NNFF architecture exploiting both rotation-invariant and covariant features separately to directly predict atomic force vectors without using spatial derivatives, thereby reducing expensive structural feature calculation by ~180-480x. This acceleration enables us to develop NNFF which directly predicts atomic forces in complex ternary and quaternary-element extended systems comprised of long polymer chains, amorphous oxide, and surface chemical reactions. The staggered rotation-invariant-covariant architecture described here can also directly predict complex covariant vector outputs from local physical structures in domains beyond computational material science.

References in corpus (16)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• 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
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Numerical atomic orbitals for linear scaling
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Building machine learning force fields for nanoclusters
• Artificial Neural Networks in Fluid Dynamics: A Novel Approach to the Navier-Stokes Equations

Cited by in corpus (12)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• Graph Neural Networks for Molecules
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Graph Neural Networks Accelerated Molecular Dynamics
• Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene
• Convolutional neural networks enable high-fidelity prediction of path-dependent diffusion barrier spectra in multi-principal element alloys
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• Unsupervised learning of atomic environments from simple features
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions