Inverse Design of a Dual-Band Reflective Polarizing Surface Using Generative Machine Learning

Parinaz Naseri; George Goussetis; Nelson J. G. Fonseca; Sean V. Hum

doi:10.23919/EuCAP53622.2022.9769267

Inverse Design of a Dual-Band Reflective Polarizing Surface Using Generative Machine Learning

Parinaz Naseri^*, George Goussetis, Nelson J. G. Fonseca, Sean V. Hum

^*Corresponding author for this work

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

7 Citations (Scopus)

Abstract

Reflective linear-to-circular polarization (LP-to-CP) converters are desired for satellite communication applications to reduce the complexity of the antenna system and the number of the required apertures in single-feed-per-beam configurations. Moreover, wideband operation and angular stability are important polarizer attributes in these applications. Here, for the first time, we use a machine-learning technique employing a generative adversarial network (GAN) to systematically and efficiently explore and exploit the solution space of single-layer structures for this problem. By using a GAN to optimize the shape of the polarizing element, superior performance in terms of overlapping axial ratio bandwidth for normal and oblique incidence of 30° compared to the previously studied designs is achieved.

Original language	English
Title of host publication	16th European Conference on Antennas and Propagation (EuCAP 2022)
Publisher	IEEE
ISBN (Electronic)	9788831299046
DOIs	https://doi.org/10.23919/EuCAP53622.2022.9769267
Publication status	Published - 11 May 2022
Event	16th European Conference on Antennas and Propagation 2022 - Madrid, Spain Duration: 27 Mar 2022 → 1 Apr 2022

Conference

Conference	16th European Conference on Antennas and Propagation 2022
Abbreviated title	EuCAP 2022
Country/Territory	Spain
City	Madrid
Period	27/03/22 → 1/04/22

Keywords

dual-band polarizer
frequency selective surface
generative adversarial network (GAN)
inverse design
machine learning
metasurface
polarization conversion
satellite communications

ASJC Scopus subject areas

Computer Networks and Communications
Electronic, Optical and Magnetic Materials
Instrumentation
Radiation

Access to Document

10.23919/EuCAP53622.2022.9769267

Cite this

@inproceedings{26de1afcee124b76a6a2bd690e61890a,

title = "Inverse Design of a Dual-Band Reflective Polarizing Surface Using Generative Machine Learning",

abstract = "Reflective linear-to-circular polarization (LP-to-CP) converters are desired for satellite communication applications to reduce the complexity of the antenna system and the number of the required apertures in single-feed-per-beam configurations. Moreover, wideband operation and angular stability are important polarizer attributes in these applications. Here, for the first time, we use a machine-learning technique employing a generative adversarial network (GAN) to systematically and efficiently explore and exploit the solution space of single-layer structures for this problem. By using a GAN to optimize the shape of the polarizing element, superior performance in terms of overlapping axial ratio bandwidth for normal and oblique incidence of 30° compared to the previously studied designs is achieved. ",

keywords = "dual-band polarizer, frequency selective surface, generative adversarial network (GAN), inverse design, machine learning, metasurface, polarization conversion, satellite communications",

author = "Parinaz Naseri and George Goussetis and Fonseca, {Nelson J. G.} and Hum, {Sean V.}",

note = "Publisher Copyright: {\textcopyright} 2022 European Association for Antennas and Propagation.; 16th European Conference on Antennas and Propagation 2022, EuCAP 2022 ; Conference date: 27-03-2022 Through 01-04-2022",

year = "2022",

month = may,

day = "11",

doi = "10.23919/EuCAP53622.2022.9769267",

language = "English",

booktitle = "16th European Conference on Antennas and Propagation (EuCAP 2022)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Inverse Design of a Dual-Band Reflective Polarizing Surface Using Generative Machine Learning

AU - Naseri, Parinaz

AU - Goussetis, George

AU - Fonseca, Nelson J. G.

AU - Hum, Sean V.

PY - 2022/5/11

Y1 - 2022/5/11

N2 - Reflective linear-to-circular polarization (LP-to-CP) converters are desired for satellite communication applications to reduce the complexity of the antenna system and the number of the required apertures in single-feed-per-beam configurations. Moreover, wideband operation and angular stability are important polarizer attributes in these applications. Here, for the first time, we use a machine-learning technique employing a generative adversarial network (GAN) to systematically and efficiently explore and exploit the solution space of single-layer structures for this problem. By using a GAN to optimize the shape of the polarizing element, superior performance in terms of overlapping axial ratio bandwidth for normal and oblique incidence of 30° compared to the previously studied designs is achieved.

AB - Reflective linear-to-circular polarization (LP-to-CP) converters are desired for satellite communication applications to reduce the complexity of the antenna system and the number of the required apertures in single-feed-per-beam configurations. Moreover, wideband operation and angular stability are important polarizer attributes in these applications. Here, for the first time, we use a machine-learning technique employing a generative adversarial network (GAN) to systematically and efficiently explore and exploit the solution space of single-layer structures for this problem. By using a GAN to optimize the shape of the polarizing element, superior performance in terms of overlapping axial ratio bandwidth for normal and oblique incidence of 30° compared to the previously studied designs is achieved.

KW - dual-band polarizer

KW - frequency selective surface

KW - generative adversarial network (GAN)

KW - inverse design

KW - machine learning

KW - metasurface

KW - polarization conversion

KW - satellite communications

UR - http://www.scopus.com/inward/record.url?scp=85130620396&partnerID=8YFLogxK

U2 - 10.23919/EuCAP53622.2022.9769267

DO - 10.23919/EuCAP53622.2022.9769267

M3 - Conference contribution

AN - SCOPUS:85130620396

BT - 16th European Conference on Antennas and Propagation (EuCAP 2022)

PB - IEEE

T2 - 16th European Conference on Antennas and Propagation 2022

Y2 - 27 March 2022 through 1 April 2022

ER -

Inverse Design of a Dual-Band Reflective Polarizing Surface Using Generative Machine Learning

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this