Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer

Samarth Kumar; Mahmoud M.T. Maghrabi; Shiva Kumar; Mohamed H. Bakr

doi:10.1117/12.3040918

Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer

Samarth Kumar^*
, Mahmoud M.T. Maghrabi
, Shiva Kumar
, Mohamed H. Bakr

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

A feedforward optical neural network (ONN) based on Silicon photonics nanocircuits is proposed for the equalization of linear and nonlinear impairments of fiber optic communication systems. The activation function is realized using a semiconductor saturable absorber mirror (SESAM) or a highly nonlinear waveguide (HNLW). The proposed ONN can be placed at the fiber optic link output just before the coherent receiver. The numerical simulation of a 28 GBaud quadrature phase shift keying (QPSK) signal over a long haul dispersion-managed fiber optic link showed that the performance can be significantly improved by using the ONN based on HNLW. The dominant impairment in the long haul dispersion managed link is the fiber nonlinearity. To illustrate that the proposed ONN can mitigate fiber dispersion, simulations of a short-haul fiber optic link consisting of a standard single mode fiber (SSMF) is carried out and results showed that the ONN based on SESAM is quite effective in mitigating the dispersive impairments of the fiber optic system.

Original language	English
Title of host publication	AI and Optical Data Sciences VI
Editors	Masaya Notomi, Tingyi Zhou
Publisher	SPIE
ISBN (Electronic)	9781510684980
DOIs	https://doi.org/10.1117/12.3040918
State	Published - 2025
Externally published	Yes
Event	AI and Optical Data Sciences VI 2025 - San Francisco, United States Duration: 27 Jan 2025 → 31 Jan 2025

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13375
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	AI and Optical Data Sciences VI 2025
Country/Territory	United States
City	San Francisco
Period	27/01/25 → 31/01/25

Bibliographical note

Publisher Copyright:
© 2025 SPIE.

Keywords

Fiber Optics
Fiber nonlinear effects
Optical Communications
Optical Neural Networks
Photonic Neural Networks

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Instrumentation
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.3040918

Cite this

Kumar, S., Maghrabi, M. M. T., Kumar, S., & Bakr, M. H. (2025). Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer. In M. Notomi, & T. Zhou (Eds.), AI and Optical Data Sciences VI Article 133750K (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13375). SPIE. https://doi.org/10.1117/12.3040918

@inproceedings{9a876d59c9ec4999886f230a79e9e002,

title = "Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer",

abstract = "A feedforward optical neural network (ONN) based on Silicon photonics nanocircuits is proposed for the equalization of linear and nonlinear impairments of fiber optic communication systems. The activation function is realized using a semiconductor saturable absorber mirror (SESAM) or a highly nonlinear waveguide (HNLW). The proposed ONN can be placed at the fiber optic link output just before the coherent receiver. The numerical simulation of a 28 GBaud quadrature phase shift keying (QPSK) signal over a long haul dispersion-managed fiber optic link showed that the performance can be significantly improved by using the ONN based on HNLW. The dominant impairment in the long haul dispersion managed link is the fiber nonlinearity. To illustrate that the proposed ONN can mitigate fiber dispersion, simulations of a short-haul fiber optic link consisting of a standard single mode fiber (SSMF) is carried out and results showed that the ONN based on SESAM is quite effective in mitigating the dispersive impairments of the fiber optic system.",

keywords = "Fiber Optics, Fiber nonlinear effects, Optical Communications, Optical Neural Networks, Photonic Neural Networks",

author = "Samarth Kumar and Maghrabi, \{Mahmoud M.T.\} and Shiva Kumar and Bakr, \{Mohamed H.\}",

note = "Publisher Copyright: {\textcopyright} 2025 SPIE.; AI and Optical Data Sciences VI 2025 ; Conference date: 27-01-2025 Through 31-01-2025",

year = "2025",

doi = "10.1117/12.3040918",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Masaya Notomi and Tingyi Zhou",

booktitle = "AI and Optical Data Sciences VI",

address = "United States",

}

Kumar, S, Maghrabi, MMT, Kumar, S & Bakr, MH 2025, Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer. in M Notomi & T Zhou (eds), AI and Optical Data Sciences VI., 133750K, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13375, SPIE, AI and Optical Data Sciences VI 2025, San Francisco, United States, 27/01/25. https://doi.org/10.1117/12.3040918

Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer. / Kumar, Samarth; Maghrabi, Mahmoud M.T.; Kumar, Shiva et al.
AI and Optical Data Sciences VI. ed. / Masaya Notomi; Tingyi Zhou. SPIE, 2025. 133750K (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13375).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer

AU - Kumar, Samarth

AU - Maghrabi, Mahmoud M.T.

AU - Kumar, Shiva

AU - Bakr, Mohamed H.

PY - 2025

Y1 - 2025

N2 - A feedforward optical neural network (ONN) based on Silicon photonics nanocircuits is proposed for the equalization of linear and nonlinear impairments of fiber optic communication systems. The activation function is realized using a semiconductor saturable absorber mirror (SESAM) or a highly nonlinear waveguide (HNLW). The proposed ONN can be placed at the fiber optic link output just before the coherent receiver. The numerical simulation of a 28 GBaud quadrature phase shift keying (QPSK) signal over a long haul dispersion-managed fiber optic link showed that the performance can be significantly improved by using the ONN based on HNLW. The dominant impairment in the long haul dispersion managed link is the fiber nonlinearity. To illustrate that the proposed ONN can mitigate fiber dispersion, simulations of a short-haul fiber optic link consisting of a standard single mode fiber (SSMF) is carried out and results showed that the ONN based on SESAM is quite effective in mitigating the dispersive impairments of the fiber optic system.

AB - A feedforward optical neural network (ONN) based on Silicon photonics nanocircuits is proposed for the equalization of linear and nonlinear impairments of fiber optic communication systems. The activation function is realized using a semiconductor saturable absorber mirror (SESAM) or a highly nonlinear waveguide (HNLW). The proposed ONN can be placed at the fiber optic link output just before the coherent receiver. The numerical simulation of a 28 GBaud quadrature phase shift keying (QPSK) signal over a long haul dispersion-managed fiber optic link showed that the performance can be significantly improved by using the ONN based on HNLW. The dominant impairment in the long haul dispersion managed link is the fiber nonlinearity. To illustrate that the proposed ONN can mitigate fiber dispersion, simulations of a short-haul fiber optic link consisting of a standard single mode fiber (SSMF) is carried out and results showed that the ONN based on SESAM is quite effective in mitigating the dispersive impairments of the fiber optic system.

KW - Fiber Optics

KW - Fiber nonlinear effects

KW - Optical Communications

KW - Optical Neural Networks

KW - Photonic Neural Networks

UR - https://www.scopus.com/pages/publications/105004553177

U2 - 10.1117/12.3040918

DO - 10.1117/12.3040918

M3 - Conference contribution

AN - SCOPUS:105004553177

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - AI and Optical Data Sciences VI

A2 - Notomi, Masaya

A2 - Zhou, Tingyi

PB - SPIE

T2 - AI and Optical Data Sciences VI 2025

Y2 - 27 January 2025 through 31 January 2025

ER -

Mitigation of Distortions in Fiber-Optic Communication Systems using Optical Neural Network-Based Equalizer

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this