Bayesian optimization for the inverse scattering problem in quantum reaction dynamics

Abstract

We propose a machine-learning approach based on Bayesian optimization to build global potential energy surfaces (PES) for reactive molecular systems using feedback from quantum scattering calculations. The method is designed to correct for the uncertainties of quantum chemistry calculations and yield potentials that reproduce accurately the reaction probabilities in a wide range of energies. These surfaces are obtained automatically and do not require manual fitting of the {\it ab initio} energies with analytical functions. The PES are built from a small number of {\it ab initio} points by an iterative process that incrementally samples the most relevant parts of the configuration space. Using the dynamical results of previous authors as targets, we show that such feedback loops produce accurate global PES with 30 {\it ab initio} energies for the three-dimensional H + H${}_2$ $\to$ H${}_2$ + H reaction and 290 {\it ab initio} energies for the six-dimensional OH + H${}_2$ $\to$ H${}_2$O + H reaction. These surfaces are obtained from 360 scattering calculations for H${}_3$ and 600 scattering calculations for OH${}_3$. We also introduce a method that quickly converges to an accurate PES without the {\it a priori} knowledge of the dynamical results. By construction, our method illustrates the lowest number of potential energy points (i.e. the minimum information) required for the non-parametric construction of global PES for quantum reactive scattering calculations.

9 pages, 8 figures

References in corpus (1)

• Feshbach resonances in ultracold 85Rb-87Rb and 6Li-87Rb mixtures

Cited by in corpus (30)

• Machine learning for electronically excited states of molecules
• Bayesian optimization for tuning and selecting hybrid-density functionals
• Bayesian machine learning for quantum molecular dynamics
• Bayesian optimization package: PHYSBO
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• Invariant Manifolds and Rate Constants in Driven Chemical Reactions
• Machine-learning-corrected quantum dynamics calculations
• Dynamics on Multiple Potential Energy Surfaces: Quantitative Studies of Elementary Processes Relevant to Hypersonics
• Bayesian optimization for inverse problems in time-dependent quantum dynamics
• Quantum Gaussian process model of potential energy surface for a polyatomic molecule
• Neural network approach for the dynamics on the normally hyperbolic invariant manifold of periodically driven systems
• Leveraging Legacy Data to Accelerate Materials Design via Preference Learning
• Transfer matrix theory of surface spin echo experiments with molecules
• Spatial mapping of disordered 2D materials: the conductance Sudoku
• Transformative Applications of Machine Learning for Chemical Reactions
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• Machine Learning Potential Energy Surfaces
• Continuous black-box optimization with quantum annealing and random subspace coding
• Decoding the conductance of disordered nanostructures: a quantum inverse problem
• Quantum transfer through small networks coupled to phonons: effects of topology vs phonons
• Deep learning regression for inverse quantum scattering
• Gradient-based reconstruction of molecular Hamiltonians and density matrices from time-dependent quantum observables
• Multi-objective optimization for retinal photoisomerization models with respect to experimental observables
• Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning
• Bayesian optimization approach for tracking the location and orientation of a moving target using far-field data
• Interpolation and extrapolation of global potential energy surfaces for polyatomic systems by Gaussian processes with composite kernels
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles