Deep learning prediction of noise-driven nonlinear instabilities in fibre optics

Abstract Machine learning is bringing revolutionary approaches into many fields of physics. Among those, photonics enables fast and scalable information processing. Photonics platforms further possess rich nonlinear dynamics that drive fundamental interest but also prove powerful for applications in...

Full description

Saved in:
Bibliographic Details
Main Authors: Yassin Boussafa, Lynn Sader, Van Thuy Hoang, Bruno P. Chaves, Alexis Bougaud, Marc Fabert, Alessandro Tonello, John M. Dudley, Michael Kues, Benjamin Wetzel
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-62713-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226125956349952
author Yassin Boussafa
Lynn Sader
Van Thuy Hoang
Bruno P. Chaves
Alexis Bougaud
Marc Fabert
Alessandro Tonello
John M. Dudley
Michael Kues
Benjamin Wetzel
author_facet Yassin Boussafa
Lynn Sader
Van Thuy Hoang
Bruno P. Chaves
Alexis Bougaud
Marc Fabert
Alessandro Tonello
John M. Dudley
Michael Kues
Benjamin Wetzel
author_sort Yassin Boussafa
collection DOAJ
description Abstract Machine learning is bringing revolutionary approaches into many fields of physics. Among those, photonics enables fast and scalable information processing. Photonics platforms further possess rich nonlinear dynamics that drive fundamental interest but also prove powerful for applications in computation, imaging, frequency conversion, source development and advanced signal processing. However, incoherent processes of nonlinear optics are hardly exploited in practice as the control of noise-driven dynamics remains challenging. Here, we exploit deep learning strategies and demonstrate that coherent optical seeding can effectively shape incoherent spectral broadening. We focus on the intricate interplay between weak coherent pulses and broadband noise, competing during nonlinear fibre propagation within an amplification process known as modulation instability. We demonstrate artificial neural networks’ capability to efficiently predict these complex incoherent dynamics, both numerically and experimentally. Our results show that input seed properties can be inferred from the incoherent output signal. Furthermore, our approach enables reliable prediction of output spectral fluctuations, paving the way to tailoring complex photonic signals with specific correlation features.
format Article
id doaj-art-3c3cf48c9968400286d7ca7c7d8926d0
institution Kabale University
issn 2041-1723
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-3c3cf48c9968400286d7ca7c7d8926d02025-08-24T11:38:09ZengNature PortfolioNature Communications2041-17232025-08-0116111410.1038/s41467-025-62713-xDeep learning prediction of noise-driven nonlinear instabilities in fibre opticsYassin Boussafa0Lynn Sader1Van Thuy Hoang2Bruno P. Chaves3Alexis Bougaud4Marc Fabert5Alessandro Tonello6John M. Dudley7Michael Kues8Benjamin Wetzel9XLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesXLIM Research Institute, CNRS UMR 7252, University of LimogesUniversité Marie et Louis Pasteur, CNRS Institut FEMTO-STInstitute of Photonics and Cluster of Excellence PhoenixD, Leibniz University HannoverXLIM Research Institute, CNRS UMR 7252, University of LimogesAbstract Machine learning is bringing revolutionary approaches into many fields of physics. Among those, photonics enables fast and scalable information processing. Photonics platforms further possess rich nonlinear dynamics that drive fundamental interest but also prove powerful for applications in computation, imaging, frequency conversion, source development and advanced signal processing. However, incoherent processes of nonlinear optics are hardly exploited in practice as the control of noise-driven dynamics remains challenging. Here, we exploit deep learning strategies and demonstrate that coherent optical seeding can effectively shape incoherent spectral broadening. We focus on the intricate interplay between weak coherent pulses and broadband noise, competing during nonlinear fibre propagation within an amplification process known as modulation instability. We demonstrate artificial neural networks’ capability to efficiently predict these complex incoherent dynamics, both numerically and experimentally. Our results show that input seed properties can be inferred from the incoherent output signal. Furthermore, our approach enables reliable prediction of output spectral fluctuations, paving the way to tailoring complex photonic signals with specific correlation features.https://doi.org/10.1038/s41467-025-62713-x
spellingShingle Yassin Boussafa
Lynn Sader
Van Thuy Hoang
Bruno P. Chaves
Alexis Bougaud
Marc Fabert
Alessandro Tonello
John M. Dudley
Michael Kues
Benjamin Wetzel
Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
Nature Communications
title Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
title_full Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
title_fullStr Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
title_full_unstemmed Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
title_short Deep learning prediction of noise-driven nonlinear instabilities in fibre optics
title_sort deep learning prediction of noise driven nonlinear instabilities in fibre optics
url https://doi.org/10.1038/s41467-025-62713-x
work_keys_str_mv AT yassinboussafa deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT lynnsader deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT vanthuyhoang deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT brunopchaves deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT alexisbougaud deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT marcfabert deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT alessandrotonello deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT johnmdudley deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT michaelkues deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics
AT benjaminwetzel deeplearningpredictionofnoisedrivennonlinearinstabilitiesinfibreoptics