The University of Southampton
University of Southampton Institutional Repository

Inverse design of structural color: Finding multiple solutions via conditional generative adversarial networks

Inverse design of structural color: Finding multiple solutions via conditional generative adversarial networks
Inverse design of structural color: Finding multiple solutions via conditional generative adversarial networks
The “one-to-many” problem is a typical challenge that faced by many machine learning aided inverse nanophotonics designs where one target optical response can be achieved by many solutions (designs). Although novel training approaches, such as tandem network, and network architecture, such as the mixture density model, have been proposed, the critical problem of solution degeneracy still exists where some possible solutions or solution spaces are discarded or unreachable during the network training process. Here, we report a solution to the “one-to-many” problem by employing a conditional generative adversarial network (cGAN) that enables generating sets of multiple solution groups to a design problem. Using the inverse design of a transmissive Fabry-Pérot-cavity-based color filter as an example, our model demonstrates the capability of generating an average number of 3.58 solution groups for each color. These multiple solutions allow the selection of the best design for each color which results in a record high accuracy with an average index color difference ΔE of 0.44. The capability of identifying multiple solution groups can benefit the design manufacturing to allow more viable designs for fabrication. The capability of our cGAN is verified experimentally by inversely designing the RGB color filters. We envisage this cGAN-based design methodology can be applied to other nanophotonic structures or physical science domains where the identification of multi-solution across a vast parameter space is required.
Fabry-Perot cavity, deep learning, generative adversarial networks, inverse design, one-to-many problem, structural color
3057-3069
Dai, Peng
1150a00a-e54b-438b-bf51-4e8521c07f66
Sun, Kai
b7c648a3-7be8-4613-9d4d-1bf937fb487b
Yan, Xingzhao
e1f3f636-74e4-42d5-81c7-04feec2b85ba
Muskens, Otto
2284101a-f9ef-4d79-8951-a6cda5bfc7f9
De Groot, Kees
92cd2e02-fcc4-43da-8816-c86f966be90c
Zhu, Xupeng
e4198221-2dee-49a8-be47-80f7291d5b9f
Hu, Yueqiang
0194aaab-f90c-4aa1-a97e-65843499b26e
Duan, Huigao
f26e2028-5fdb-4d42-8054-3c07ddd5325d
Huang, Ruomeng
c6187811-ef2f-4437-8333-595c0d6ac978
Dai, Peng
1150a00a-e54b-438b-bf51-4e8521c07f66
Sun, Kai
b7c648a3-7be8-4613-9d4d-1bf937fb487b
Yan, Xingzhao
e1f3f636-74e4-42d5-81c7-04feec2b85ba
Muskens, Otto
2284101a-f9ef-4d79-8951-a6cda5bfc7f9
De Groot, Kees
92cd2e02-fcc4-43da-8816-c86f966be90c
Zhu, Xupeng
e4198221-2dee-49a8-be47-80f7291d5b9f
Hu, Yueqiang
0194aaab-f90c-4aa1-a97e-65843499b26e
Duan, Huigao
f26e2028-5fdb-4d42-8054-3c07ddd5325d
Huang, Ruomeng
c6187811-ef2f-4437-8333-595c0d6ac978

Dai, Peng, Sun, Kai, Yan, Xingzhao, Muskens, Otto, De Groot, Kees, Zhu, Xupeng, Hu, Yueqiang, Duan, Huigao and Huang, Ruomeng (2022) Inverse design of structural color: Finding multiple solutions via conditional generative adversarial networks. Nanophotonics, 11 (13), 3057-3069. (doi:10.1515/nanoph-2022-0095).

Record type: Article

Abstract

The “one-to-many” problem is a typical challenge that faced by many machine learning aided inverse nanophotonics designs where one target optical response can be achieved by many solutions (designs). Although novel training approaches, such as tandem network, and network architecture, such as the mixture density model, have been proposed, the critical problem of solution degeneracy still exists where some possible solutions or solution spaces are discarded or unreachable during the network training process. Here, we report a solution to the “one-to-many” problem by employing a conditional generative adversarial network (cGAN) that enables generating sets of multiple solution groups to a design problem. Using the inverse design of a transmissive Fabry-Pérot-cavity-based color filter as an example, our model demonstrates the capability of generating an average number of 3.58 solution groups for each color. These multiple solutions allow the selection of the best design for each color which results in a record high accuracy with an average index color difference ΔE of 0.44. The capability of identifying multiple solution groups can benefit the design manufacturing to allow more viable designs for fabrication. The capability of our cGAN is verified experimentally by inversely designing the RGB color filters. We envisage this cGAN-based design methodology can be applied to other nanophotonic structures or physical science domains where the identification of multi-solution across a vast parameter space is required.

Text
Inverse Design of Structural Color Finding Multiple Solutions via Conditional Generative Adversarial Networks - Accepted Manuscript
Available under License Creative Commons Attribution.
Download (1MB)
Text
Supplementary Materials of Inverse Design of Structural Color Finding Multiple Solutions via Conditional Generative Adversarial Networks - Version of Record
Available under License Creative Commons Attribution.
Download (4MB)
Text
10.1515_nanoph-2022-0095 - Version of Record
Available under License Creative Commons Attribution.
Download (2MB)

More information

Submitted date: 21 February 2022
Accepted/In Press date: 2 May 2022
e-pub ahead of print date: 16 May 2022
Keywords: Fabry-Perot cavity, deep learning, generative adversarial networks, inverse design, one-to-many problem, structural color

Identifiers

Local EPrints ID: 457322
URI: http://eprints.soton.ac.uk/id/eprint/457322
PURE UUID: 83e3e3ac-4c3e-4406-8fda-b38ee41a54db
ORCID for Otto Muskens: ORCID iD orcid.org/0000-0003-0693-5504
ORCID for Kees De Groot: ORCID iD orcid.org/0000-0002-3850-7101
ORCID for Ruomeng Huang: ORCID iD orcid.org/0000-0003-1185-635X

Catalogue record

Date deposited: 01 Jun 2022 16:37
Last modified: 13 Jul 2022 01:44

Export record

Altmetrics

Contributors

Author: Peng Dai
Author: Kai Sun
Author: Xingzhao Yan
Author: Otto Muskens ORCID iD
Author: Kees De Groot ORCID iD
Author: Xupeng Zhu
Author: Yueqiang Hu
Author: Huigao Duan
Author: Ruomeng Huang ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×