Controlling spatiotemporal nonlinearities in multimode fibers with deep neural networks

TL;DR

This paper introduces a deep neural network-based method to control and optimize nonlinear frequency conversion in multimode fibers by tailoring the pump beam profile, enabling precise spectral tuning of broadband sources.

Contribution

It is the first to apply machine learning for controlling nonlinear interactions in multimode fibers through tailored excitation conditions.

Findings

Neural networks successfully learn the relation between beam profile and spectrum.

Network-suggested beam shapes enable control over Raman scattering and supercontinuum.

The method allows for tuning the spectra of broadband fiber sources.

Abstract

Spatiotemporal nonlinear interactions in multimode fibers are of interest for beam shaping and frequency conversion by exploiting the nonlinear propagation of different pump regimes from quasi-continuous wave to ultrashort pulses centered around visible to infrared pump wavelengths. The nonlinear effects in multi-mode fibers depend strongly on the excitation condition, however relatively little work has been reported on this subject. Here, we present the first machine learning approach to learn and control the nonlinear frequency conversion inside multimode fibers by tailoring the excitation condition via deep neural networks. Trained with experimental data, deep neural networks are adapted to learn the relation between the spatial beam profile of the pump pulse and the spectrum generation. For different user-defined target spectra, network-suggested beam shapes are applied and control over the cascaded Raman scattering and supercontinuum generation processes are achieved. Our results present a novel method to tune the spectra of a broadband source.