Design of Pixelated Wideband Metasurface Absorber Using Transfer Learning and Generative Adversarial Networks
Source abstract
Abstract
In this paper, a wideband metasurface absorber is proposed by utilizing transfer learning and a conditional deep convolutional generative adversarial network (CDCGAN). This approach involves introducing a forward prediction neural network to predict the spectral curve of a metasurface absorber, as well as a generative adversarial network for the inverse design of a metasurface absorber. After comparing different pre-trained models, a transfer learning network (TLN) based on GoogleNet-InceptionV3 is incorporated into the design process to reduce the amount of training data required. Based on the pixelated metasurface with a common effect of metallic pixels and resistive film pixels, a broadband electromagnetic absorber was designed through the CDCGAN model. For the application target of the C-band, a pixelated broadband metasurface Absorber I has been designed, which can achieve an absorption effect of less than −8 dB in the range of 6.5–8 GHz, and the absorption performance reaches less than −15 dB near the resonant frequency point of 7 GHz. Further lightweight optimization design was carried out, and the metasurface Absorber II was designed for application in the X-band, which has an absorption bandwidth below −8 dB at 9–12 GHz. The reflectivity curve measured by the experiment is in good agreement with that of the simulation result. Of note, our methodology aims to reversely engineer suitable absorbing structures based on customer-defined spectrums, which may bear some significance to the rapid design of broadband metasurface absorbers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metamaterials and Metasurfaces Applications · Antenna Design and Analysis · Advanced Antenna and Metasurface Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
School of Physics and Mechanics, Wuhan University of Technology, Wuhan 430070, China
School of Integrated Circuits, Nanjing University of Information Science and Technology, Nanjing 210044, China
Funding
Hubei Provincial Natural Science Foundation under Grant
References (40)
Show source-provided references
1. Performing Mathematical Operations with Metamaterials10.1126/science.1242818 ↗
2. High Performance Bianisotropic Metasurfaces: Asymmetric Transmission of Light10.1103/PhysRevLett.113.023902 ↗
3. Full Stokes Polarimetry for Wide-Angle Incident Light10.1002/pssr.202000044 ↗
4. Flat Optics with Designer Metasurfaces10.1038/nmat3839 ↗
5. A Broadband Achromatic Metalens in the Visible10.1038/s41565-017-0052-4 ↗
6. Octave Bandwidth Photonic Fishnet-Achromatic-Metalens10.1038/s41467-020-17015-9 ↗
7. Light Propagation with Phase Discontinuities: Generalized Laws of Reflection and Refraction10.1126/science.1210713 ↗
8. Dispersionless Phase Discontinuities for Controlling Light Propagation10.1021/nl303031j ↗
9. Negative Index of Refraction in Optical Metamaterials10.1364/OL.30.003356 ↗
10. Metamaterials and Negative Refractive Index10.1126/science.1096796 ↗
11. Three-Dimensional Invisibility Cloak at Optical Wavelengths10.1126/science.1186351 ↗
12. Three-Dimensional Broadband Ground-Plane Cloak Made of Metamaterials10.1038/ncomms1023 ↗
13. A Frequency Selective Rasorber with Absorption Bands on Both Sides of Passband Based on Screen-Printed Resistive Film10.1109/LAWP.2024.3436912 ↗
14. Design and Simulation of a Wideband, Wide-Angle and Polarization-Insensitive Microwave Absorber Based on Pattern Optimization of Resistive Films10.1088/1361-6463/abbb46 ↗
15. Broadband Absorber of Impedance Dispersion Lossy Patterned Resistive Films10.1088/1361-6463/ab8513 ↗
16. Ultra-Thin Broadband Metamaterial Absorber10.1007/s00339-012-6936-0 ↗
17. A Route to Unusually Broadband Plasmonic Absorption Spanning from Visible to Mid-Infrared10.1007/s11468-019-00916-x ↗
18. Independently Switchable Rasorber with Wide Transmission and Low-Reflection Bands Under Dual Polarization10.1109/TMTT.2023.3298190 ↗
19. A Polarization-Independent Wideband Switchable Rasorber with High Roll-Off Characteristics Utilizing Third-Order Switchable FSS10.1109/LAWP.2024.3514899 ↗
20. Review of Broadband Metamaterial Absorbers: From Principles, Design Strategies, and Tunable Properties to Functional Applications10.1002/adfm.202213818 ↗
21. Coding Metamaterials, Digital Metamaterials and Programmable Metamaterials10.1038/lsa.2014.99 ↗
22. Machine-Learning Designs of Anisotropic Digital Coding Metasurfaces10.1002/adts.201800132 ↗
23. Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials10.1021/acsnano.8b03569 ↗
24. Physics-Based Approach for a Neural Networks Enabled Design of All-Dielectric Metasurfaces10.1021/acsphotonics.0c00663 ↗
25. Efficient Spectrum Prediction and Inverse Design for Plasmonic Waveguide Systems Based on Artificial Neural Networks10.1364/PRJ.7.000368 ↗
26. Phase-to-Pattern Inverse Design Paradigm for Fast Realization of Functional Metasurfaces via Transfer Learning10.1038/s41467-021-23087-y ↗
27. Migrating Knowledge between Physical Scenarios Based on Artificial Neural Networks10.1021/acsphotonics.8b01526 ↗
28. Generative Model for the Inverse Design of Metasurfaces10.1021/acs.nanolett.8b03171 ↗
29. Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks10.1021/acsnano.9b02371 ↗
30. Deep Learning Enabled Inverse Design in Nanophotonics10.1515/nanoph-2019-0474 ↗
31. Multiplexing the Aperture of a Metasurface: Inverse Design via Deep-Learning-Forward Genetic Algorithm10.1088/1361-6463/aba64f ↗
32. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
33. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
34. Salehinejad, H., Valaee, S., Dowdell, T., Colak, E., and Barfett, J. (2018, January 15–20). Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461430 ↗
35. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv.
36. A Case Study of Conditional Deep Convolutional Generative Adversarial Networks in Machine Fault Diagnosis10.1007/s10845-020-01579-w ↗
37. Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv.
38. Inverse Design of Transmission-Type Linear-to-Circular Polarization Control Metasurface Based on Deep Learning10.1088/1361-6463/acefdf ↗
39. A Deep Learning Approach for Inverse Design of the Metasurface for Dual-Polarized Waves10.1007/s00339-021-05030-6 ↗
40. Generative Adversarial Networks for High Degree of Freedom Metasurface Designs10.1007/s42114-024-01190-0 ↗