Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy

Abstract

An efficient and trajectory-free active learning method is proposed to automatically sample data points for constructing globally accurate reactive potential energy surfaces (PESs) using neural networks (NNs). Although NNs do not provide the predictive variance as the Gaussian process regression does, we can alternatively minimize the negative of the squared difference surface (NSDS) given by two different NN models to actively locate the point where the PES is least confident. A batch of points in the minima of this NSDS can be iteratively added into the training set to improve the PES. The configuration space is gradually and globally covered with no need to run classical trajectory (or equivalently molecular dynamics) simulations. Through refitting the available analytical PESs of H3 and OH3 reactive systems, we demonstrate the efficiency and robustness of this new strategy, which enables fast convergence of the reactive PESs with respect to the number of points in terms of quantum scattering probabilities.

References in corpus (7)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• A machine learning-based selective sampling procedure for identifying the low energy region in a potential energy surface: a case study on proton conduction in oxides
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Ready, set and no action: A static perspective on potential energy surfaces commonly used in gas-surface dynamics

Cited by in corpus (11)

• Machine learning for electronically excited states of molecules
• Perspective on integrating machine learning into computational chemistry and materials science
• Committee neural network potentials control generalization errors and enable active learning
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Machine learning and excited-state molecular dynamics
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Atomistic structure search using local surrogate mode
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Active Learning Approach to Optimization of Experimental Control
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning