Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks
Optical metasurfaces enable compact, lightweight and planar optical devices. Their performances, however, are still limited by design approximations imposed by their macroscopic dimensions. To address this problem, we propose a neural network-based multi-stage gradient optimization method to efficie...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/12/7/738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849417998036631552 |
|---|---|
| author | Yongle Zhou Qi Xu Yikun Liu Emiliano R. Martins Haowen Liang Juntao Li |
| author_facet | Yongle Zhou Qi Xu Yikun Liu Emiliano R. Martins Haowen Liang Juntao Li |
| author_sort | Yongle Zhou |
| collection | DOAJ |
| description | Optical metasurfaces enable compact, lightweight and planar optical devices. Their performances, however, are still limited by design approximations imposed by their macroscopic dimensions. To address this problem, we propose a neural network-based multi-stage gradient optimization method to efficiently modulate nonlocal interactions between meta-atoms, which is one of the major effects neglected by current design methods. Our strategy allows for the use of these interactions as an additional design dimension to enhance the performance of metasurfaces and can be used to optimize large-scale metasurfaces with multiple parameters. As an example of application, we design a meta-hologram with a zero-order energy suppressed to 26% (theoretically) and 57% (experimentally) of its original value. Our results suggest that neural networks can be used as a powerful design tool for the next generation of high-performance metasurfaces with complex functionalities. |
| format | Article |
| id | doaj-art-8d097945802f41d79ab37dccbf103a95 |
| institution | Kabale University |
| issn | 2304-6732 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj-art-8d097945802f41d79ab37dccbf103a952025-08-20T03:32:33ZengMDPI AGPhotonics2304-67322025-07-0112773810.3390/photonics12070738Nonlocal Interactions in Metasurfaces Harnessed by Neural NetworksYongle Zhou0Qi Xu1Yikun Liu2Emiliano R. Martins3Haowen Liang4Juntao Li5State Key Laboratory of Optoelectronic Materials and Technologies, School of Physics, Sun Yat-sen University, Guangzhou 510275, ChinaState Key Laboratory of Optoelectronic Materials and Technologies, School of Physics, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Provincial Key Laboratory of Quantum Metrology and Sensing, School of Physics and Astronomy, Sun Yat-Sen University, Zhuhai 519080, ChinaSão Carlos School of Engineering, Department of Electrical and Computer Engineering, University of São Paulo, São Carlos 13566-590, SP, BrazilState Key Laboratory of Optoelectronic Materials and Technologies, School of Physics, Sun Yat-sen University, Guangzhou 510275, ChinaState Key Laboratory of Optoelectronic Materials and Technologies, School of Physics, Sun Yat-sen University, Guangzhou 510275, ChinaOptical metasurfaces enable compact, lightweight and planar optical devices. Their performances, however, are still limited by design approximations imposed by their macroscopic dimensions. To address this problem, we propose a neural network-based multi-stage gradient optimization method to efficiently modulate nonlocal interactions between meta-atoms, which is one of the major effects neglected by current design methods. Our strategy allows for the use of these interactions as an additional design dimension to enhance the performance of metasurfaces and can be used to optimize large-scale metasurfaces with multiple parameters. As an example of application, we design a meta-hologram with a zero-order energy suppressed to 26% (theoretically) and 57% (experimentally) of its original value. Our results suggest that neural networks can be used as a powerful design tool for the next generation of high-performance metasurfaces with complex functionalities.https://www.mdpi.com/2304-6732/12/7/738nonlocal interactionsmeta-hologramneural networkzero-order |
| spellingShingle | Yongle Zhou Qi Xu Yikun Liu Emiliano R. Martins Haowen Liang Juntao Li Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks Photonics nonlocal interactions meta-hologram neural network zero-order |
| title | Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks |
| title_full | Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks |
| title_fullStr | Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks |
| title_full_unstemmed | Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks |
| title_short | Nonlocal Interactions in Metasurfaces Harnessed by Neural Networks |
| title_sort | nonlocal interactions in metasurfaces harnessed by neural networks |
| topic | nonlocal interactions meta-hologram neural network zero-order |
| url | https://www.mdpi.com/2304-6732/12/7/738 |
| work_keys_str_mv | AT yonglezhou nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks AT qixu nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks AT yikunliu nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks AT emilianormartins nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks AT haowenliang nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks AT juntaoli nonlocalinteractionsinmetasurfacesharnessedbyneuralnetworks |