An overview of deep-learning models for metasurface design and optimization

Muhammad Fizan; Sadia Noureen; Muhammad Zubair; Muhammad Qasim Mehmood; Yehia Massoud

doi:10.1117/12.2686202

An overview of deep-learning models for metasurface design and optimization

Muhammad Fizan, Sadia Noureen, Muhammad Zubair, Muhammad Qasim Mehmood, Yehia Massoud

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

Abstract

Deep Neural Networks (DNNs) have emerged as a powerful tool for predicting the structure and composition of diverse nanophotonic devices based on their desired response. These techniques have played a pivotal role in driving advancements across a spectrum of fields within optics and photonics. Notably, they have significantly contributed to the progress and innovation observed in the domains of plasmonics, holography, chirality, topological photonics, airy beams, color filters, vortex beams, and absorbers. This paper reviews the most recent advances in using Machine Learning (ML) and Deep Learning (DL) for inverse design of nanophotonic devices. In the past, conventional optimization techniques have been used as a design tool to optimize the metasurface and nanodevice structures but in recent years ML and DL based techniques have revolutionized this process. These techniquese are more time efficient and accurate.

Original language	English (US)
Title of host publication	Nanophotonics and Micro/Nano Optics IX
Editors	Zhiping Zhou, Kazumi Wada, Limin Tong
Publisher	SPIE
ISBN (Electronic)	9781510667952
DOIs	https://doi.org/10.1117/12.2686202
State	Published - 2023
Event	Nanophotonics and Micro/Nano Optics IX 2023 - Beijing, China Duration: Oct 14 2023 → Oct 16 2023

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	12773
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Nanophotonics and Micro/Nano Optics IX 2023
Country/Territory	China
City	Beijing
Period	10/14/23 → 10/16/23

Bibliographical note

Publisher Copyright:
© 2023 SPIE. All rights reserved.

Keywords

chirality
Deep Learning (DL)
Deep Neural Networks (DNN)
holography
Machine Learning (ML)
nanophotonic devices
plasmonics

ASJC Scopus subject areas

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

Access to Document

10.1117/12.2686202

Cite this

Fizan, M., Noureen, S., Zubair, M., Mehmood, M. Q., & Massoud, Y. (2023). An overview of deep-learning models for metasurface design and optimization. In Z. Zhou, K. Wada, & L. Tong (Eds.), Nanophotonics and Micro/Nano Optics IX Article 127731G (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12773). SPIE. https://doi.org/10.1117/12.2686202

@inproceedings{8ea1670f499a41feaa56056baebd4a20,

title = "An overview of deep-learning models for metasurface design and optimization",

abstract = "Deep Neural Networks (DNNs) have emerged as a powerful tool for predicting the structure and composition of diverse nanophotonic devices based on their desired response. These techniques have played a pivotal role in driving advancements across a spectrum of fields within optics and photonics. Notably, they have significantly contributed to the progress and innovation observed in the domains of plasmonics, holography, chirality, topological photonics, airy beams, color filters, vortex beams, and absorbers. This paper reviews the most recent advances in using Machine Learning (ML) and Deep Learning (DL) for inverse design of nanophotonic devices. In the past, conventional optimization techniques have been used as a design tool to optimize the metasurface and nanodevice structures but in recent years ML and DL based techniques have revolutionized this process. These techniquese are more time efficient and accurate.",

keywords = "chirality, Deep Learning (DL), Deep Neural Networks (DNN), holography, Machine Learning (ML), nanophotonic devices, plasmonics",

author = "Muhammad Fizan and Sadia Noureen and Muhammad Zubair and Mehmood, {Muhammad Qasim} and Yehia Massoud",

year = "2023",

doi = "10.1117/12.2686202",

language = "English (US)",

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

publisher = "SPIE",

editor = "Zhiping Zhou and Kazumi Wada and Limin Tong",

booktitle = "Nanophotonics and Micro/Nano Optics IX",

address = "United States",

}

Fizan, M, Noureen, S, Zubair, M, Mehmood, MQ & Massoud, Y 2023, An overview of deep-learning models for metasurface design and optimization. in Z Zhou, K Wada & L Tong (eds), Nanophotonics and Micro/Nano Optics IX., 127731G, Proceedings of SPIE - The International Society for Optical Engineering, vol. 12773, SPIE, Nanophotonics and Micro/Nano Optics IX 2023, Beijing, China, 10/14/23. https://doi.org/10.1117/12.2686202

An overview of deep-learning models for metasurface design and optimization. / Fizan, Muhammad; Noureen, Sadia; Zubair, Muhammad et al.
Nanophotonics and Micro/Nano Optics IX. ed. / Zhiping Zhou; Kazumi Wada; Limin Tong. SPIE, 2023. 127731G (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12773).

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

TY - GEN

T1 - An overview of deep-learning models for metasurface design and optimization

AU - Fizan, Muhammad

AU - Noureen, Sadia

AU - Zubair, Muhammad

AU - Mehmood, Muhammad Qasim

AU - Massoud, Yehia

PY - 2023

Y1 - 2023

N2 - Deep Neural Networks (DNNs) have emerged as a powerful tool for predicting the structure and composition of diverse nanophotonic devices based on their desired response. These techniques have played a pivotal role in driving advancements across a spectrum of fields within optics and photonics. Notably, they have significantly contributed to the progress and innovation observed in the domains of plasmonics, holography, chirality, topological photonics, airy beams, color filters, vortex beams, and absorbers. This paper reviews the most recent advances in using Machine Learning (ML) and Deep Learning (DL) for inverse design of nanophotonic devices. In the past, conventional optimization techniques have been used as a design tool to optimize the metasurface and nanodevice structures but in recent years ML and DL based techniques have revolutionized this process. These techniquese are more time efficient and accurate.

AB - Deep Neural Networks (DNNs) have emerged as a powerful tool for predicting the structure and composition of diverse nanophotonic devices based on their desired response. These techniques have played a pivotal role in driving advancements across a spectrum of fields within optics and photonics. Notably, they have significantly contributed to the progress and innovation observed in the domains of plasmonics, holography, chirality, topological photonics, airy beams, color filters, vortex beams, and absorbers. This paper reviews the most recent advances in using Machine Learning (ML) and Deep Learning (DL) for inverse design of nanophotonic devices. In the past, conventional optimization techniques have been used as a design tool to optimize the metasurface and nanodevice structures but in recent years ML and DL based techniques have revolutionized this process. These techniquese are more time efficient and accurate.

KW - chirality

KW - Deep Learning (DL)

KW - Deep Neural Networks (DNN)

KW - holography

KW - Machine Learning (ML)

KW - nanophotonic devices

KW - plasmonics

UR - http://www.scopus.com/inward/record.url?scp=85182022162&partnerID=8YFLogxK

U2 - 10.1117/12.2686202

DO - 10.1117/12.2686202

M3 - Conference contribution

AN - SCOPUS:85182022162

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

BT - Nanophotonics and Micro/Nano Optics IX

A2 - Zhou, Zhiping

A2 - Wada, Kazumi

A2 - Tong, Limin

PB - SPIE

T2 - Nanophotonics and Micro/Nano Optics IX 2023

Y2 - 14 October 2023 through 16 October 2023

ER -

An overview of deep-learning models for metasurface design and optimization

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this