Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules

Abstract

Machine learning for predicting control landscape maps of full quantum molecular dynamics is examined through a case study of the laser-induced three-dimensional (3D) alignment of asymmetric top molecules, an essential technique for observing and/or manipulating molecular dynamics in a molecule-fixed frame. We consider the "prolate-type" asymmetryic top molecules with the asymmetry parameters $-1<\kappa <0$ and the C2v symmetry in the low-temperature limiting case, which are aligned by using mutually orthogonal linearly polarized double laser pulses. The landscape map for each molecule consists of 6000 pixels, each pixel of which represents the maximum degree of alignment achieved by each set of control parameters. After examining ways to deal with the markedly different molecular parameters in a unified manner for suitably training a convolutional neural network (CNN) model, we train the CNN model by using 55 training sample molecules to predict the control landscape maps of 35 test sample molecules with reasonably high accuracy. As the predicted landscape maps provide a big picture of the alignment control, we show, for example, that the double pulse control scheme is especially effective for a molecule having a polarizability component that is much larger in value than the other two components.

arXiv comment33 pages, 6 figures, 2 tables

References in corpus (16)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Control of quantum phenomena: Past, present, and future
• Machine learning for electronically excited states of molecules
• Quantum control of molecular rotation
• Laser-induced alignment and orientation of quantum-state-selected large molecules
• Towards self-driving laboratories: The central role of density functional theory in the AI age
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Quantum optimal control of multi-level dissipative quantum systems with Reinforcement Learning
• Computational studies of x-ray scattering from three-dimensionally-aligned asymmetric-top molecules
• A comparative study of different machine learning methods for dissipative quantum dynamics
• Predicting quantum dynamical cost landscapes with deep learning
• Alignment of asymmetric-top molecules using multiple-pulse trains
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Versatile linkage: a family of space-conserving strategies for agglomerative hierarchical clustering
• Machine-learning-inspired quantum control in many-body dynamics