On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces
Chiral metasurfaces have been widely used in sensing, imaging and other fields because they can manipulate light through the efficient circular dichroism (CD). However, its on-demand design is still a very challenging task. In this work, we propose an on-demand multiple reverse design based on deep...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Results in Physics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211379722006386 |
| _version_ | 1811250712791744512 |
|---|---|
| author | Zheyu Hou Chenglong Zheng Jie Li Pengyu Zhang Suozai Li Shipu Zheng Jian Shen Jianquan Yao Chaoyang Li |
| author_facet | Zheyu Hou Chenglong Zheng Jie Li Pengyu Zhang Suozai Li Shipu Zheng Jian Shen Jianquan Yao Chaoyang Li |
| author_sort | Zheyu Hou |
| collection | DOAJ |
| description | Chiral metasurfaces have been widely used in sensing, imaging and other fields because they can manipulate light through the efficient circular dichroism (CD). However, its on-demand design is still a very challenging task. In this work, we propose an on-demand multiple reverse design based on deep learning, named target-driven conditional generative network (TCGN). It can reverse design the metasurface structure that meets the required CD, and its mean square error (MAE) is 0.0089. We use this method to inversely design multiple sets of metasurfaces with different structures, and all their CD values can exceed 0.36. Both simulations and experiments prove the feasibility and effectiveness of using deep learning to reverse design metasurfaces. In addition, the designed metasurface can realize chiral wavefront control under dual frequency. This design method based on deep learning can rapidly and efficiently design the chiral metasurfaces, which provides a new way for the design of metasurfaces. |
| first_indexed | 2024-04-12T16:08:44Z |
| format | Article |
| id | doaj.art-396976e9040c4eedb6446f0ee85dacc3 |
| institution | Directory Open Access Journal |
| issn | 2211-3797 |
| language | English |
| last_indexed | 2024-04-12T16:08:44Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Physics |
| spelling | doaj.art-396976e9040c4eedb6446f0ee85dacc32022-12-22T03:25:58ZengElsevierResults in Physics2211-37972022-11-0142106024On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfacesZheyu Hou0Chenglong Zheng1Jie Li2Pengyu Zhang3Suozai Li4Shipu Zheng5Jian Shen6Jianquan Yao7Chaoyang Li8School of Information and Communication Engineering, Hainan University, Haikou 570228, China; State Key Laboratory of Marine Resource Utilization in South China Sea, Hainan University, Haikou 570228, ChinaKey Laboratory of Opto-Electronics Information Technology (Tianjin University), Ministry of Education, School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Opto-Electronics Information Technology (Tianjin University), Ministry of Education, School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, China; State Key Laboratory of Marine Resource Utilization in South China Sea, Hainan University, Haikou 570228, ChinaChina Electronics Corporation Hainan Joint Innovation Research Institute Co. Ltd, Chengmai 571924, ChinaChina Electronics Corporation Hainan Joint Innovation Research Institute Co. Ltd, Chengmai 571924, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, China; State Key Laboratory of Marine Resource Utilization in South China Sea, Hainan University, Haikou 570228, China; Corresponding authors at: School of Information and Communication Engineering, Hainan University, Haikou 570228, China (J. Shen); Key Laboratory of Opto-Electronics Information Technology (Tianjin University), Ministry of Education, School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China (J. Yao).Key Laboratory of Opto-Electronics Information Technology (Tianjin University), Ministry of Education, School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China; Corresponding authors at: School of Information and Communication Engineering, Hainan University, Haikou 570228, China (J. Shen); Key Laboratory of Opto-Electronics Information Technology (Tianjin University), Ministry of Education, School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China (J. Yao).School of Information and Communication Engineering, Hainan University, Haikou 570228, China; State Key Laboratory of Marine Resource Utilization in South China Sea, Hainan University, Haikou 570228, ChinaChiral metasurfaces have been widely used in sensing, imaging and other fields because they can manipulate light through the efficient circular dichroism (CD). However, its on-demand design is still a very challenging task. In this work, we propose an on-demand multiple reverse design based on deep learning, named target-driven conditional generative network (TCGN). It can reverse design the metasurface structure that meets the required CD, and its mean square error (MAE) is 0.0089. We use this method to inversely design multiple sets of metasurfaces with different structures, and all their CD values can exceed 0.36. Both simulations and experiments prove the feasibility and effectiveness of using deep learning to reverse design metasurfaces. In addition, the designed metasurface can realize chiral wavefront control under dual frequency. This design method based on deep learning can rapidly and efficiently design the chiral metasurfaces, which provides a new way for the design of metasurfaces.http://www.sciencedirect.com/science/article/pii/S2211379722006386Chiral metasurfacesTerahertzDeep learningReverse design |
| spellingShingle | Zheyu Hou Chenglong Zheng Jie Li Pengyu Zhang Suozai Li Shipu Zheng Jian Shen Jianquan Yao Chaoyang Li On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces Results in Physics Chiral metasurfaces Terahertz Deep learning Reverse design |
| title | On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces |
| title_full | On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces |
| title_fullStr | On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces |
| title_full_unstemmed | On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces |
| title_short | On-demand design based on deep learning and phase manipulation of all-silicon terahertz chiral metasurfaces |
| title_sort | on demand design based on deep learning and phase manipulation of all silicon terahertz chiral metasurfaces |
| topic | Chiral metasurfaces Terahertz Deep learning Reverse design |
| url | http://www.sciencedirect.com/science/article/pii/S2211379722006386 |
| work_keys_str_mv | AT zheyuhou ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT chenglongzheng ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT jieli ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT pengyuzhang ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT suozaili ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT shipuzheng ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT jianshen ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT jianquanyao ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces AT chaoyangli ondemanddesignbasedondeeplearningandphasemanipulationofallsiliconterahertzchiralmetasurfaces |