Design and experiment of terahertz unidirectional transmission structure based on neural network
In metasurface design, massive meta-atoms have to be optimized to produce the desired properties, which are time-consuming and sometimes prohibitive. In this paper, neural network model composed forward modeling and inverse design network is proposed to realize rapid, efficient, and automatic metasu...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Results in Physics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211379723001560 |
| _version_ | 1797851970276425728 |
|---|---|
| author | Shoujian Ouyang Jianwei Xu Shouxin Duan Danni Ye Yun Shen Xiaohua Deng |
| author_facet | Shoujian Ouyang Jianwei Xu Shouxin Duan Danni Ye Yun Shen Xiaohua Deng |
| author_sort | Shoujian Ouyang |
| collection | DOAJ |
| description | In metasurface design, massive meta-atoms have to be optimized to produce the desired properties, which are time-consuming and sometimes prohibitive. In this paper, neural network model composed forward modeling and inverse design network is proposed to realize rapid, efficient, and automatic metasurface design of THz unidirectional transmission. Specifically, massive metasurface samples are generated by Python-CST co-simulation to train the neural network model and make it robust to predict the THz responses and vice versa. The consistency of simulation and prediction results imply that the model can accurately capture the nonintuitive complex relationship between structural parameters and electromagnetic spectra. To further verify the model, retrieved structural parameters for unidirectional transmission are deduced due to inverse design network and double L-shape arrays metasurface is experimental fabricated. It is shown that the experimental asymmetric transmission responses by retrieved structural parameters are identical with the simulations by design parameter. Such results effectively verify the design and model, providing a paradigm for functional metasurface design and the development of applications in optoelectrical fields. |
| first_indexed | 2024-04-09T19:25:21Z |
| format | Article |
| id | doaj.art-3c4d566bdb284274ac4c0114ceb13de0 |
| institution | Directory Open Access Journal |
| issn | 2211-3797 |
| language | English |
| last_indexed | 2024-04-09T19:25:21Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Physics |
| spelling | doaj.art-3c4d566bdb284274ac4c0114ceb13de02023-04-05T08:13:12ZengElsevierResults in Physics2211-37972023-04-0147106363Design and experiment of terahertz unidirectional transmission structure based on neural networkShoujian Ouyang0Jianwei Xu1Shouxin Duan2Danni Ye3Yun Shen4Xiaohua Deng5Department of Physics, School of Physics and Materials Science, Nanchang University, Nanchang 330031, China; Institute of Space Science and Technology, Nanchang University, Nanchang 330031, ChinaDepartment of Physics, School of Physics and Materials Science, Nanchang University, Nanchang 330031, China; Institute of Space Science and Technology, Nanchang University, Nanchang 330031, ChinaDepartment of Physics, School of Physics and Materials Science, Nanchang University, Nanchang 330031, China; Institute of Space Science and Technology, Nanchang University, Nanchang 330031, ChinaDepartment of Measuring and Controlling Technology and Instrument, Institute of Advanced Manufacturing, Nanchang University, Nanchang 330031, ChinaDepartment of Physics, School of Physics and Materials Science, Nanchang University, Nanchang 330031, China; Institute of Space Science and Technology, Nanchang University, Nanchang 330031, China; Corresponding author at: Department of Physics, School of Physics and Materials Science, Nanchang University, Nanchang 330031, China.Institute of Space Science and Technology, Nanchang University, Nanchang 330031, ChinaIn metasurface design, massive meta-atoms have to be optimized to produce the desired properties, which are time-consuming and sometimes prohibitive. In this paper, neural network model composed forward modeling and inverse design network is proposed to realize rapid, efficient, and automatic metasurface design of THz unidirectional transmission. Specifically, massive metasurface samples are generated by Python-CST co-simulation to train the neural network model and make it robust to predict the THz responses and vice versa. The consistency of simulation and prediction results imply that the model can accurately capture the nonintuitive complex relationship between structural parameters and electromagnetic spectra. To further verify the model, retrieved structural parameters for unidirectional transmission are deduced due to inverse design network and double L-shape arrays metasurface is experimental fabricated. It is shown that the experimental asymmetric transmission responses by retrieved structural parameters are identical with the simulations by design parameter. Such results effectively verify the design and model, providing a paradigm for functional metasurface design and the development of applications in optoelectrical fields.http://www.sciencedirect.com/science/article/pii/S2211379723001560Neural networkUnidirectional transmissionMetasurface |
| spellingShingle | Shoujian Ouyang Jianwei Xu Shouxin Duan Danni Ye Yun Shen Xiaohua Deng Design and experiment of terahertz unidirectional transmission structure based on neural network Results in Physics Neural network Unidirectional transmission Metasurface |
| title | Design and experiment of terahertz unidirectional transmission structure based on neural network |
| title_full | Design and experiment of terahertz unidirectional transmission structure based on neural network |
| title_fullStr | Design and experiment of terahertz unidirectional transmission structure based on neural network |
| title_full_unstemmed | Design and experiment of terahertz unidirectional transmission structure based on neural network |
| title_short | Design and experiment of terahertz unidirectional transmission structure based on neural network |
| title_sort | design and experiment of terahertz unidirectional transmission structure based on neural network |
| topic | Neural network Unidirectional transmission Metasurface |
| url | http://www.sciencedirect.com/science/article/pii/S2211379723001560 |
| work_keys_str_mv | AT shoujianouyang designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork AT jianweixu designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork AT shouxinduan designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork AT danniye designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork AT yunshen designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork AT xiaohuadeng designandexperimentofterahertzunidirectionaltransmissionstructurebasedonneuralnetwork |