An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning
A hybrid framework for solving the non-uniqueness problem in the inverse design of isomorphic metasurfaces is proposed. The framework consists of a representation learning (RL) module and a variational autoencoder-particle swarm optimization (VAE-PSO) algorithm module. The RL module is used to reduc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/12/1844 |
| _version_ | 1797487989134196736 |
|---|---|
| author | Jian Zhang Jin Yuan Chuanzhen Li Bin Li |
| author_facet | Jian Zhang Jin Yuan Chuanzhen Li Bin Li |
| author_sort | Jian Zhang |
| collection | DOAJ |
| description | A hybrid framework for solving the non-uniqueness problem in the inverse design of isomorphic metasurfaces is proposed. The framework consists of a representation learning (RL) module and a variational autoencoder-particle swarm optimization (VAE-PSO) algorithm module. The RL module is used to reduce the complex high-dimensional space into a low-dimensional space with obvious features, with the purpose of eliminating the many-to-one relationship between the original design space and response space. The VAE-PSO algorithm first encodes all meta-atoms into a continuous latent space through VAE and then applies PSO to search for an optimized latent vector whose corresponding metasurface fulfills the target response. This framework gives the solution paradigm of the ideal non-uniqueness situation, simplifies the complexity of the network, improves the running speed of the PSO algorithm, and obtains the global optimal solution with 94% accuracy on the test set. |
| first_indexed | 2024-03-09T23:56:40Z |
| format | Article |
| id | doaj.art-a323634973e94b73b6bb4c5490e2f706 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T23:56:40Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-a323634973e94b73b6bb4c5490e2f7062023-11-23T16:24:37ZengMDPI AGElectronics2079-92922022-06-011112184410.3390/electronics11121844An Inverse Design Framework for Isotropic Metasurfaces Based on Representation LearningJian Zhang0Jin Yuan1Chuanzhen Li2Bin Li3State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, ChinaState Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, ChinaState Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, ChinaState Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, ChinaA hybrid framework for solving the non-uniqueness problem in the inverse design of isomorphic metasurfaces is proposed. The framework consists of a representation learning (RL) module and a variational autoencoder-particle swarm optimization (VAE-PSO) algorithm module. The RL module is used to reduce the complex high-dimensional space into a low-dimensional space with obvious features, with the purpose of eliminating the many-to-one relationship between the original design space and response space. The VAE-PSO algorithm first encodes all meta-atoms into a continuous latent space through VAE and then applies PSO to search for an optimized latent vector whose corresponding metasurface fulfills the target response. This framework gives the solution paradigm of the ideal non-uniqueness situation, simplifies the complexity of the network, improves the running speed of the PSO algorithm, and obtains the global optimal solution with 94% accuracy on the test set.https://www.mdpi.com/2079-9292/11/12/1844metasurfacesrepresentation learningvariational autoencoderinverse design |
| spellingShingle | Jian Zhang Jin Yuan Chuanzhen Li Bin Li An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning Electronics metasurfaces representation learning variational autoencoder inverse design |
| title | An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning |
| title_full | An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning |
| title_fullStr | An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning |
| title_full_unstemmed | An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning |
| title_short | An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning |
| title_sort | inverse design framework for isotropic metasurfaces based on representation learning |
| topic | metasurfaces representation learning variational autoencoder inverse design |
| url | https://www.mdpi.com/2079-9292/11/12/1844 |
| work_keys_str_mv | AT jianzhang aninversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT jinyuan aninversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT chuanzhenli aninversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT binli aninversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT jianzhang inversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT jinyuan inversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT chuanzhenli inversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning AT binli inversedesignframeworkforisotropicmetasurfacesbasedonrepresentationlearning |