Reducing the cost of neural network potential generation for reactive molecular systems

Abstract

Although machine-learning potentials have recently had substantial impact on molecular simulations, the construction of a robust training set can still become a limiting factor, especially due to the requirement of a reference ab initio simulation that covers all the relevant geometries of the system. Recognizing that this can be prohibitive for certain systems, we develop the method of transition tube sampling that mitigates the computational cost of training set and model generation. In this approach, we generate classical or quantum thermal geometries around a transition path describing a conformational change or a chemical reaction using only a sparse set of local normal mode expansions along this path and select from these geometries by an active learning protocol. This yields a training set with geometries that characterize the whole transition without the need for a costly reference trajectory. The performance of the method is evaluated on different molecular systems with the complexity of the potential energy landscape increasing from a single minimum to a double proton-transfer reaction with high barriers. Our results show that the method leads to training sets that give rise to models applicable in classical and path integral simulations alike that are on par with those based directly on ab initio calculations while providing the computational speed-up we have come to expect from machine-learning potentials.

References in corpus (24)

• Canonical sampling through velocity-rescaling
• Separable Dual Space Gaussian Pseudo-potentials
• CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations
• PLUMED 2: New feathers for an old bird
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• PLUMED: a portable plugin for free-energy calculations with molecular dynamics
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Statistically optimal analysis of samples from multiple equilibrium states
• Less is more: sampling chemical space with active learning
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• How van der Waals interactions determine the unique properties of water
• Efficient stochastic thermostatting of path integral molecular dynamics
• Nuclear quantum effects in solids using a colored-noise thermostat
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Committee neural network potentials control generalization errors and enable active learning
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Accurate molecular dynamics and nuclear quantum effects at low cost by multiple steps in real and imaginary time: using density functional theory to accelerate wavefunction methods
• Potential energy surface interpolation with neural networks for instanton rate calculations
• Significance of nuclear quantum effects in hydrogen bonded molecular chains

Cited by in corpus (3)

• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Physics-informed active learning for accelerating quantum chemical simulations