Machine-learning-corrected quantum dynamics calculations

Abstract

Quantum scattering calculations for all but low-dimensional systems at low energies must rely on approximations. All approximations introduce errors. The impact of these errors is often difficult to assess because they depend on the Hamiltonian parameters and the particular observable under study. Here, we illustrate a general, system and approximation-independent, approach to improve the accuracy of quantum dynamics approximations. The method is based on a Bayesian machine learning (BML) algorithm that is trained by a small number of rigorous results and a large number of approximate calculations, resulting in ML models that accurately capture the dependence of the dynamics results on the quantum dynamics parameters. Most importantly, the present work demonstrates that the BML models can generalize quantum results to different dynamical processes. Thus, a ML model trained by a combination of approximate and rigorous results for a certain inelastic transition can make accurate predictions for different transitions without rigorous calculations. This opens the possibility of improving the accuracy of approximate calculations for quantum transitions that are out of reach of rigorous scattering calculations.

arXiv comment6 pages, 4 figures

References in corpus (18)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Rotational quenching of CO due to H${}_2$ collisions
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Molecular excitation in the Interstellar Medium: recent advances in collisional, radiative and chemical processes
• Machine Learning Phases of Strongly Correlated Fermions
• Fermionic neural-network states for ab-initio electronic structure
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Solving the Bose-Hubbard model with machine learning
• Bayesian machine learning for quantum molecular dynamics
• Quantum dynamics of CO-H${}_2$ in full dimensionality
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Gaussian Process Model for Collision Dynamics of Complex Molecules
• Stereodynamical control of a quantum scattering resonance in cold molecular collisions
• Full-dimensional Quantum Dynamics of SiO in Collision with H${}_2$
• Few-particle Green's functions for strongly correlated systems on infinite lattices

Cited by in corpus (9)

• Perspective on integrating machine learning into computational chemistry and materials science
• Optimal control of quantum thermal machines using machine learning
• Bayesian optimization for inverse problems in time-dependent quantum dynamics
• Quantum Extreme Learning of molecular potential energy surfaces and force fields
• Rainbow scattering in rotationally inelastic collisions of HCl and H${}_2$
• Cavity-Heisenberg spin-$j$ chain quantum battery and reinforcement learning optimization
• A Data-Driven Machine Learning Approach for Electron-Molecule Ionization Cross Sections
• Extrapolation of polaron properties to low phonon frequencies by Bayesian machine learning
• Neural network ensemble for computing cross sections for rotational transitions in H${}_2$O + H${}_2$O collisions