Staff View: Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons

Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons

We theoretically investigate the plasmonic properties of mid-infrared graphene-based metamaterials and apply deep learning of a neural network for the inverse design. These artificial structures have square periodic arrays of graphene plasmonic resonators deposited on dielectric thin films. Optical...

Full description

Saved in:

Bibliographic Details
Main Authors:	Phan, Anh D., Nguyen, Cuong V., Pham, T. Linh, Tran, V. Huynh, Vu, D. Lam, Le, Anh-Tuan, Wakabayashi, Katsunori
Format:	Article
Language:	English
Published:	MDPI 2020
Subjects:	graphene metamaterials deep learning inverse design plasmonics
Online Access:	https://dlib.phenikaa-uni.edu.vn/handle/PNK/403 https://doi.org/10.3390/cryst10020125
Tags:	Add Tag No Tags, Be the first to tag this record!

id	oai:localhost:PNK-403
record_format	dspace
spelling	oai:localhost:PNK-4032022-08-17T05:54:37Z Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons Phan, Anh D. Nguyen, Cuong V. Pham, T. Linh Tran, V. Huynh Vu, D. Lam Le, Anh-Tuan Wakabayashi, Katsunori graphene metamaterials deep learning inverse design plasmonics We theoretically investigate the plasmonic properties of mid-infrared graphene-based metamaterials and apply deep learning of a neural network for the inverse design. These artificial structures have square periodic arrays of graphene plasmonic resonators deposited on dielectric thin films. Optical spectra vary significantly with changes in structural parameters. To validate our theoretical approach, we carry out finite difference time domain simulations and compare computational results with theoretical calculations. Quantitatively good agreements among theoretical predictions, simulations, and previous experiments allow us to employ this proposed theoretical model to generate reliable data for training and testing deep neural networks. By merging the pre-trained neural network with the inverse network, we implement calculations for inverse design of the graphene-based metameterials. We also discuss the limitation of the data-driven approach. 2020-06-26T06:45:15Z 2020-06-26T06:45:15Z 2020 Article Working Paper https://dlib.phenikaa-uni.edu.vn/handle/PNK/403 https://doi.org/10.3390/cryst10020125 en application/pdf MDPI
institution	Digital Phenikaa
collection	Digital Phenikaa
language	English
topic	graphene metamaterials deep learning inverse design plasmonics
spellingShingle	graphene metamaterials deep learning inverse design plasmonics Phan, Anh D. Nguyen, Cuong V. Pham, T. Linh Tran, V. Huynh Vu, D. Lam Le, Anh-Tuan Wakabayashi, Katsunori Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
description	We theoretically investigate the plasmonic properties of mid-infrared graphene-based metamaterials and apply deep learning of a neural network for the inverse design. These artificial structures have square periodic arrays of graphene plasmonic resonators deposited on dielectric thin films. Optical spectra vary significantly with changes in structural parameters. To validate our theoretical approach, we carry out finite difference time domain simulations and compare computational results with theoretical calculations. Quantitatively good agreements among theoretical predictions, simulations, and previous experiments allow us to employ this proposed theoretical model to generate reliable data for training and testing deep neural networks. By merging the pre-trained neural network with the inverse network, we implement calculations for inverse design of the graphene-based metameterials. We also discuss the limitation of the data-driven approach.
format	Article
author	Phan, Anh D. Nguyen, Cuong V. Pham, T. Linh Tran, V. Huynh Vu, D. Lam Le, Anh-Tuan Wakabayashi, Katsunori
author_facet	Phan, Anh D. Nguyen, Cuong V. Pham, T. Linh Tran, V. Huynh Vu, D. Lam Le, Anh-Tuan Wakabayashi, Katsunori
author_sort	Phan, Anh D.
title	Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
title_short	Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
title_full	Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
title_fullStr	Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
title_full_unstemmed	Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons
title_sort	deep learning for the inverse design of mid-infrared graphene plasmons
publisher	MDPI
publishDate	2020
url	https://dlib.phenikaa-uni.edu.vn/handle/PNK/403 https://doi.org/10.3390/cryst10020125
_version_	1751856272760635392
score	8.887836

Deep Learning for the Inverse Design of Mid-Infrared Graphene Plasmons

Similar Items