Accelerating Atomistic Simulations with Piecewise Machine Learned Ab Initio Potentials at Classical Force Field-like Cost

Abstract

Machine learning methods have nowadays become easy-to-use tools for constructing high-dimensional interatomic potentials with ab initio accuracy. Although machine learned interatomic potentials are generally orders of magnitude faster than first-principles calculations, they remain much slower than classical force fields, at the price of using more complex structural descriptors. To bridge this efficiency gap, we propose an embedded atom neural network approach with simple piecewise switching function based descriptors, resulting in a favorable linear scaling with the number of neighbor atoms. Numerical examples validate that this piecewise machine learning model can be over an order of magnitude faster than various popular machine learned potentials with comparable accuracy for both metallic and covalent materials, approaching the speed of the fastest embedded atom method (i.e. several μs/atom per CPU core). The extreme efficiency of this approach promises its potential in first-principles atomistic simulations of very large systems and/or in long timescale.

arXiv commentThis work has been accepted by Physical Chemistry Chemical Physics

References in corpus (18)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• 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
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• How van der Waals interactions determine the unique properties of water
• Ab initio thermodynamics of liquid and solid water
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Machine Learning Exciton Dynamics
• Bayesian machine learning for quantum molecular dynamics
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Conceptual and practical bases for the high accuracy of machine learning interatomic potential

Cited by in corpus (6)

• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials
• Reaction dynamics for the Cl(${}^2$P) + XCl $\to$ XCl + Cl(${}^2$P) (X = H, D, Mu) reaction on a high-fidelity ground state potential energy surface
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems