Machine learning for ultrafast nonlinear fibre photonics

Christophe Finot; Sonia Boscolo; Junsong Peng; Andrei Ermolaev; Anastasiia Sheveleva; John M. Dudley

doi:10.1109/ICTON62926.2024.10647546

Machine learning for ultrafast nonlinear fibre photonics

Christophe Finot, Sonia Boscolo, Junsong Peng, Andrei Ermolaev, Anastasiia Sheveleva, John M. Dudley

Aston Institute of Photonic Technologies (AiPT)

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

We provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024)
Editors	Francesco Prudenzano, Marian Marciniak
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	979-8-3503-7730-9
ISBN (Print)	979-8-3503-7730-9
DOIs	https://doi.org/10.1109/ICTON62926.2024.10647546
Publication status	Published - 2 Sept 2024
Event	2024 24th International Conference on Transparent Optical Network - Polytechnic University of Bari, Bari, Italy Duration: 14 Jul 2024 → 18 Jul 2024 https://icton2024.fbk.eu/home

Publication series

Name	International Conference on Transparent Optical Networks
ISSN (Print)	2162-7339

Conference

Conference	2024 24th International Conference on Transparent Optical Network
Abbreviated title	ICTON 2024
Country/Territory	Italy
City	Bari
Period	14/07/24 → 18/07/24
Internet address	https://icton2024.fbk.eu/home

Bibliographical note

Copyright © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

machine-learning
nonlinear fiber photonics
ultrafast nonlinear optics

Access to Document

10.1109/ICTON62926.2024.10647546

Cite this

Finot, C., Boscolo, S., Peng, J., Ermolaev, A., Sheveleva, A., & Dudley, J. M. (2024). Machine learning for ultrafast nonlinear fibre photonics. In F. Prudenzano, & M. Marciniak (Eds.), Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024) Article Tu.B1.5 (International Conference on Transparent Optical Networks). IEEE. https://doi.org/10.1109/ICTON62926.2024.10647546

@inproceedings{c2cf134d1c254543b1b6044930524802,

title = "Machine learning for ultrafast nonlinear fibre photonics",

abstract = "We provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.",

keywords = "machine-learning, nonlinear fiber photonics, ultrafast nonlinear optics",

author = "Christophe Finot and Sonia Boscolo and Junsong Peng and Andrei Ermolaev and Anastasiia Sheveleva and Dudley, {John M.}",

note = "Copyright {\textcopyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2024 24th International Conference on Transparent Optical Network, ICTON 2024 ; Conference date: 14-07-2024 Through 18-07-2024",

year = "2024",

month = sep,

day = "2",

doi = "10.1109/ICTON62926.2024.10647546",

language = "English",

isbn = "979-8-3503-7730-9",

series = "International Conference on Transparent Optical Networks",

publisher = "IEEE",

editor = "Francesco Prudenzano and Marian Marciniak",

booktitle = "Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024)",

address = "United States",

url = "https://icton2024.fbk.eu/home",

}

Finot, C, Boscolo, S, Peng, J, Ermolaev, A, Sheveleva, A & Dudley, JM 2024, Machine learning for ultrafast nonlinear fibre photonics. in F Prudenzano & M Marciniak (eds), Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024)., Tu.B1.5, International Conference on Transparent Optical Networks, IEEE, 2024 24th International Conference on Transparent Optical Network, Bari, Italy, 14/07/24. https://doi.org/10.1109/ICTON62926.2024.10647546

Machine learning for ultrafast nonlinear fibre photonics. / Finot, Christophe; Boscolo, Sonia; Peng, Junsong et al.
Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024). ed. / Francesco Prudenzano; Marian Marciniak. IEEE, 2024. Tu.B1.5 (International Conference on Transparent Optical Networks).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Machine learning for ultrafast nonlinear fibre photonics

AU - Finot, Christophe

AU - Boscolo, Sonia

AU - Peng, Junsong

AU - Ermolaev, Andrei

AU - Sheveleva, Anastasiia

AU - Dudley, John M.

N1 - Copyright © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2024/9/2

Y1 - 2024/9/2

N2 - We provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.

AB - We provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.

KW - machine-learning

KW - nonlinear fiber photonics

KW - ultrafast nonlinear optics

UR - https://ieeexplore.ieee.org/document/10647546/

UR - http://www.scopus.com/inward/record.url?scp=85204034325&partnerID=8YFLogxK

U2 - 10.1109/ICTON62926.2024.10647546

DO - 10.1109/ICTON62926.2024.10647546

M3 - Conference publication

SN - 979-8-3503-7730-9

T3 - International Conference on Transparent Optical Networks

BT - Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024)

A2 - Prudenzano, Francesco

A2 - Marciniak, Marian

PB - IEEE

T2 - 2024 24th International Conference on Transparent Optical Network

Y2 - 14 July 2024 through 18 July 2024

ER -

Finot C, Boscolo S, Peng J, Ermolaev A, Sheveleva A, Dudley JM. Machine learning for ultrafast nonlinear fibre photonics. In Prudenzano F, Marciniak M, editors, Proceedings of the 24th International Conference on Transparent Optical Networks (ICTON 2024). IEEE. 2024. Tu.B1.5. (International Conference on Transparent Optical Networks). Epub 2024 Sept 2. doi: 10.1109/ICTON62926.2024.10647546

Machine learning for ultrafast nonlinear fibre photonics

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Embargoed Document

Fingerprint

Cite this