Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning
Surface symmetry breaking and disorder have been recently explored to overcome operation bandwidth, unwanted diffraction, and polarization dependence issues in the conventional metasurface designs thanks to their increasing degrees of design freedom. However, efficient full‐wave simulation and optim...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2023-04-01
|
| Series: | Advanced Photonics Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/adpr.202200099 |
| _version_ | 1797849150922948608 |
|---|---|
| author | Yihan Ma Jonas Florentin Kolb Achintha Avin Ihalage Andre Sarker Andy Yang Hao |
| author_facet | Yihan Ma Jonas Florentin Kolb Achintha Avin Ihalage Andre Sarker Andy Yang Hao |
| author_sort | Yihan Ma |
| collection | DOAJ |
| description | Surface symmetry breaking and disorder have been recently explored to overcome operation bandwidth, unwanted diffraction, and polarization dependence issues in the conventional metasurface designs thanks to their increasing degrees of design freedom. However, efficient full‐wave simulation and optimization of electrically large electromagnetic structures have been a longstanding problem. Herein, an interactive learning approach is developed to build new meta‐atom datasets which include the effect of mutual coupling. A deep learning‐based model is developed to extract features of incident/reflection waves and their neighboring interaction responses from a limited number of known meta‐atoms. Finally, the deep neural network is incorporated with optimization algorithms to design, as an example, large‐scale metasurfaces for beam manipulation and wideband scattering reduction. The results demonstrate that the proposed architecture can be successfully applied to rapidly design aperture‐efficient metasurfaces or metalenses at large scales of over tens of thousands of meta‐atoms. |
| first_indexed | 2024-04-09T18:39:13Z |
| format | Article |
| id | doaj.art-0db1a396c95a417ab17c4939737cbaf6 |
| institution | Directory Open Access Journal |
| issn | 2699-9293 |
| language | English |
| last_indexed | 2024-04-09T18:39:13Z |
| publishDate | 2023-04-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Advanced Photonics Research |
| spelling | doaj.art-0db1a396c95a417ab17c4939737cbaf62023-04-11T06:47:35ZengWiley-VCHAdvanced Photonics Research2699-92932023-04-0144n/an/a10.1002/adpr.202200099Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive LearningYihan Ma0Jonas Florentin Kolb1Achintha Avin Ihalage2Andre Sarker Andy3Yang Hao4School of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UKSchool of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UKSchool of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UKSchool of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UKSchool of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS UKSurface symmetry breaking and disorder have been recently explored to overcome operation bandwidth, unwanted diffraction, and polarization dependence issues in the conventional metasurface designs thanks to their increasing degrees of design freedom. However, efficient full‐wave simulation and optimization of electrically large electromagnetic structures have been a longstanding problem. Herein, an interactive learning approach is developed to build new meta‐atom datasets which include the effect of mutual coupling. A deep learning‐based model is developed to extract features of incident/reflection waves and their neighboring interaction responses from a limited number of known meta‐atoms. Finally, the deep neural network is incorporated with optimization algorithms to design, as an example, large‐scale metasurfaces for beam manipulation and wideband scattering reduction. The results demonstrate that the proposed architecture can be successfully applied to rapidly design aperture‐efficient metasurfaces or metalenses at large scales of over tens of thousands of meta‐atoms.https://doi.org/10.1002/adpr.202200099deep learningmetasurfacemutual couplingnonperiodic structure |
| spellingShingle | Yihan Ma Jonas Florentin Kolb Achintha Avin Ihalage Andre Sarker Andy Yang Hao Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning Advanced Photonics Research deep learning metasurface mutual coupling nonperiodic structure |
| title | Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning |
| title_full | Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning |
| title_fullStr | Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning |
| title_full_unstemmed | Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning |
| title_short | Incorporating Meta‐Atom Interactions in Rapid Optimization of Large‐Scale Disordered Metasurfaces Based on Deep Interactive Learning |
| title_sort | incorporating meta atom interactions in rapid optimization of large scale disordered metasurfaces based on deep interactive learning |
| topic | deep learning metasurface mutual coupling nonperiodic structure |
| url | https://doi.org/10.1002/adpr.202200099 |
| work_keys_str_mv | AT yihanma incorporatingmetaatominteractionsinrapidoptimizationoflargescaledisorderedmetasurfacesbasedondeepinteractivelearning AT jonasflorentinkolb incorporatingmetaatominteractionsinrapidoptimizationoflargescaledisorderedmetasurfacesbasedondeepinteractivelearning AT achinthaavinihalage incorporatingmetaatominteractionsinrapidoptimizationoflargescaledisorderedmetasurfacesbasedondeepinteractivelearning AT andresarkerandy incorporatingmetaatominteractionsinrapidoptimizationoflargescaledisorderedmetasurfacesbasedondeepinteractivelearning AT yanghao incorporatingmetaatominteractionsinrapidoptimizationoflargescaledisorderedmetasurfacesbasedondeepinteractivelearning |