Artificial neural networks for nonlinear pulse shaping in optical fibers

Sonia Boscolo; Christophe Finot

doi:10.1016/j.optlastec.2020.106439

Artificial neural networks for nonlinear pulse shaping in optical fibers

Sonia Boscolo, Christophe Finot^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of the
nonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.

Original language	English
Article number	106439
Number of pages	7
Journal	Optics and Laser Technology
Volume	131
Early online date	3 Jul 2020
DOIs	https://doi.org/10.1016/j.optlastec.2020.106439
Publication status	Published - Nov 2020

Bibliographical note

Keywords

Neural networks
Nonlinear propagation
Optical fibers
Pulse shaping

Access to Document

10.1016/j.optlastec.2020.106439

Artificial neural networks for nonlinear pulse shaping in optical fibers
© 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Accepted author manuscript, 910 KBLicence: CC BY-NC-ND 3.0

https://arxiv.org/ftp/arxiv/papers/2002/2002.08815.pdf

Cite this

@article{57bcc67b76b045cf924a51e8f7e209bb,

title = "Artificial neural networks for nonlinear pulse shaping in optical fibers",

abstract = "We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of thenonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.",

keywords = "Neural networks, Nonlinear propagation, Optical fibers, Pulse shaping",

author = "Sonia Boscolo and Christophe Finot",

note = "{\textcopyright} 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/",

year = "2020",

month = nov,

doi = "10.1016/j.optlastec.2020.106439",

language = "English",

volume = "131",

journal = "Optics and Laser Technology",

issn = "0030-3992",

publisher = "Elsevier",

}

TY - JOUR

T1 - Artificial neural networks for nonlinear pulse shaping in optical fibers

AU - Boscolo, Sonia

AU - Finot, Christophe

PY - 2020/11

Y1 - 2020/11

N2 - We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of thenonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.

AB - We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of thenonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.

KW - Neural networks

KW - Nonlinear propagation

KW - Optical fibers

KW - Pulse shaping

UR - http://www.scopus.com/inward/record.url?scp=85087329142&partnerID=8YFLogxK

U2 - 10.1016/j.optlastec.2020.106439

DO - 10.1016/j.optlastec.2020.106439

M3 - Article

SN - 0030-3992

VL - 131

JO - Optics and Laser Technology

JF - Optics and Laser Technology

M1 - 106439

ER -

Artificial neural networks for nonlinear pulse shaping in optical fibers

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this