Deep neural network-based automatic metasurface design with a wide frequency range

Abstract Beyond the scope of conventional metasurface, which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurface design. In this paper, benefiting from Deep Neural Network (DNN), an inverse de...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Fardin Ghorbani, Sina Beyraghi, Javad Shabanpour, Homayoon Oraizi, Hossein Soleimani, Mohammad Soleimani
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6ddb4d8fd4794af39fa08837cff13b83
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6ddb4d8fd4794af39fa08837cff13b83
record_format	dspace
spelling	oai:doaj.org-article:6ddb4d8fd4794af39fa08837cff13b832021-12-02T13:26:28ZDeep neural network-based automatic metasurface design with a wide frequency range10.1038/s41598-021-86588-22045-2322https://doaj.org/article/6ddb4d8fd4794af39fa08837cff13b832021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86588-2https://doaj.org/toc/2045-2322Abstract Beyond the scope of conventional metasurface, which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurface design. In this paper, benefiting from Deep Neural Network (DNN), an inverse design procedure of a metasurface in an ultra-wide working frequency band is presented in which the output unit cell structure can be directly computed by a specified design target. To reach the highest working frequency for training the DNN, we consider 8 ring-shaped patterns to generate resonant notches at a wide range of working frequencies from 4 to 45 GHz. We propose two network architectures. In one architecture, we restrict the output of the DNN, so the network can only generate the metasurface structure from the input of 8 ring-shaped patterns. This approach drastically reduces the computational time, while keeping the network’s accuracy above 91%. We show that our model based on DNN can satisfactorily generate the output metasurface structure with an average accuracy of over 90% in both network architectures. Determination of the metasurface structure directly without time-consuming optimization procedures, an ultra-wide working frequency, and high average accuracy equip an inspiring platform for engineering projects without the need for complex electromagnetic theory.Fardin GhorbaniSina BeyraghiJavad ShabanpourHomayoon OraiziHossein SoleimaniMohammad SoleimaniNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Fardin Ghorbani Sina Beyraghi Javad Shabanpour Homayoon Oraizi Hossein Soleimani Mohammad Soleimani Deep neural network-based automatic metasurface design with a wide frequency range
description	Abstract Beyond the scope of conventional metasurface, which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurface design. In this paper, benefiting from Deep Neural Network (DNN), an inverse design procedure of a metasurface in an ultra-wide working frequency band is presented in which the output unit cell structure can be directly computed by a specified design target. To reach the highest working frequency for training the DNN, we consider 8 ring-shaped patterns to generate resonant notches at a wide range of working frequencies from 4 to 45 GHz. We propose two network architectures. In one architecture, we restrict the output of the DNN, so the network can only generate the metasurface structure from the input of 8 ring-shaped patterns. This approach drastically reduces the computational time, while keeping the network’s accuracy above 91%. We show that our model based on DNN can satisfactorily generate the output metasurface structure with an average accuracy of over 90% in both network architectures. Determination of the metasurface structure directly without time-consuming optimization procedures, an ultra-wide working frequency, and high average accuracy equip an inspiring platform for engineering projects without the need for complex electromagnetic theory.
format	article
author	Fardin Ghorbani Sina Beyraghi Javad Shabanpour Homayoon Oraizi Hossein Soleimani Mohammad Soleimani
author_facet	Fardin Ghorbani Sina Beyraghi Javad Shabanpour Homayoon Oraizi Hossein Soleimani Mohammad Soleimani
author_sort	Fardin Ghorbani
title	Deep neural network-based automatic metasurface design with a wide frequency range
title_short	Deep neural network-based automatic metasurface design with a wide frequency range
title_full	Deep neural network-based automatic metasurface design with a wide frequency range
title_fullStr	Deep neural network-based automatic metasurface design with a wide frequency range
title_full_unstemmed	Deep neural network-based automatic metasurface design with a wide frequency range
title_sort	deep neural network-based automatic metasurface design with a wide frequency range
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6ddb4d8fd4794af39fa08837cff13b83
work_keys_str_mv	AT fardinghorbani deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange AT sinabeyraghi deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange AT javadshabanpour deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange AT homayoonoraizi deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange AT hosseinsoleimani deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange AT mohammadsoleimani deepneuralnetworkbasedautomaticmetasurfacedesignwithawidefrequencyrange
_version_	1718393035497144320

Deep neural network-based automatic metasurface design with a wide frequency range

Ejemplares similares