Dispersion Characterization and Pulse Prediction with Machine Learning

TL;DR

This paper demonstrates how neural networks can effectively characterize dispersive media and predict pulse propagation, simplifying experimental procedures and enhancing optical communication and sensing applications.

Contribution

The work introduces a neural network-based method for dispersion characterization and pulse prediction that requires only a single probe pulse, reducing complexity compared to traditional methods.

Findings

Neural networks accurately predict pulse profiles and dispersive features.

The method simplifies dispersion characterization by eliminating the need for frequency scanning.

Predictions closely match experimental data.

Abstract

In this work we demonstrate the efficacy of neural networks in the characterization of dispersive media. We also develop a neural network to make predictions for input probe pulses which propagate through a nonlinear dispersive medium, which may be applied to predicting optimal pulse shapes for a desired output. The setup requires only a single pulse for the probe, providing considerable simplification of the current method of dispersion characterization that requires frequency scanning across the entirety of the gain and absorption features. We show that the trained networks are able to predict pulse profiles as well as dispersive features that are nearly identical to their experimental counterparts. We anticipate that the use of machine learning in conjunction with optical communication and sensing methods, both classical and quantum, can provide signal enhancement and experimental simplifications even in the face of highly complex, layered nonlinear light-matter interactions.