Classification and prediction of wave chaotic systems with machine learning techniques

Abstract

The wave properties of complex scattering systems that are large compared to the wavelength, and show chaos in the classical limit, are extremely sensitive to system details. A solution to the wave equation for a specific configuration can change substantially under small perturbations. Due to this extreme sensitivity, it is difficult to discern basic information about a complex system simply from scattering data as a function of energy or frequency, at least by eye. In this work, we employ supervised machine learning algorithms to reveal and classify hidden information about the complex scattering system presented in the data. As an example we are able to distinguish the total number of connected cavities in a linear chain of weakly coupled lossy enclosures from measured reflection data. A predictive machine learning algorithm for the future states of a perturbed complex scattering system is also trained with a recurrent neural network. Given a finite training data series, the reflection/transmission properties can be forecast by the proposed algorithm.

References in corpus (17)

• Machine learning phases of matter
• The Statistical Theory of Quantum Dots
• Machine learning out-of-equilibrium phases of matter
• Dynamical Energy Analysis - determining wave energy distributions in complex vibro-acoustical structures
• Statistics of Impedance and Scattering Matrices in Chaotic Microwave Cavities: Single Channel Case
• Automated tuning of inter-dot tunnel couplings in quantum dot arrays
• Statistics of Impedance and Scattering Matrices of Chaotic Microwave Cavities with Multiple Ports
• Universal Properties of 2-Port Scattering, Impedance and Admittance Matrices of Wave Chaotic Systems
• Random Matrix Theory Approach to Chaotic Coherent Perfect Absorbers
• Nonlinear Time-Reversal in a Wave Chaotic System
• The effect of short ray trajectories on the scattering statistics of wave chaotic systems
• Experimental Examination of the Effect of Short Ray Trajectories in Two-port Wave-Chaotic Scattering Systems
• Spectral properties of Dirac billiards at the van Hove singularities
• Nonlinear Time-Reversal of Classical Waves: Experiment and Model
• Focusing Waves at Arbitrary Locations in a Ray-Chaotic Enclosure Using Time-Reversed Synthetic Sonas
• Machine learning with observers predicts complex spatiotemporal behavior
• Uncovering Universal Wave Fluctuations In a Scaled Ray-Chaotic Cavity With Remote Injection

Cited by in corpus (6)

• Optimized Analog Information Multiplexing Across Custom-Tailored MetaCavity Configurations
• Efficient Statistical Model for Predicting Electromagnetic Wave Distribution in Coupled Enclosures
• Wave scattering properties of multiple weakly-coupled complex systems
• Eigenfunction and eigenmode-spacing statistics in chaotic photonic crystal graphs
• Time Domain Generalization of the Random Coupling Model and Experimental Verification in a Complex Scattering System
• Deep learning estimation of complex reverberant wave fields by a programmable metasurface