Inverse Design of Electromagnetic‐Induced Transparency Metasurface Using Conditional Generative Adversarial Network
Open Access
- 28 October 2026
- journal article
- research article
- Published by Wiley in Advanced Intelligent Systems
- p. e70611
Abstract
Traditional metasurface inverse design methods suffer from intensive manual modeling, laborious data collection, and extensive numerical calculations, leading to a compromised design efficiency and accuracy. To solve these drawbacks, this paper proposes a metasurface inverse design method using a conditional generative adversarial network (CGAN). A dataset construction framework integrating modeling, simulation, and response processing is established to ease data samples collection and reduce manual workload. Different from conventional parameterized modeling, the metasurface unit patterns are constructed by using a pixel‐based graphical modeling method based on encoding matrices. Furthermore, Gramian Angle Fields (GAFs) are incorporated to explore the latent physical correlations in electromagnetic responses, effectively improving the quality of generated metasurface structure images. By embedding an optimized U‐Net architecture into the CGAN model to suppress gradient vanishing and improve training stability and resolution, high‐precision mapping from target responses to metasurface structures is realized. An electromagnetically induced transparency (EIT) metasurface validates the proposed method. The results demonstrate that the proposed method achieves lower MSE, fewer training epochs, and less training cost. The simulated transmission spectra of the designed metasurface agree well with the target spectra with an average spectral accuracy above 90%, exhibiting promising application potentials for metasurfaces inverse design.Keywords
Funding Information
- National Natural Science Foundation of China (6210619762571128W252107262371136)
This publication has 22 references indexed in Scilit:
- Inverse design of cylindrical curved shell metasurface for elastic wave modulation based on PSO-BP modelThin-Walled Structures, 2025
- A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface designNeural Networks, 2024
- All-dielectric achromatic hole-array metasurfacesJournal of Physics D: Applied Physics, 2024
- Inverse design of two-function transmission-type reconfigurable polarization control metasurfaces based on deep learningJournal of Physics D: Applied Physics, 2024
- Efficient design method for terahertz broadband metasurface patterns via deep learningOptics & Laser Technology, 2022
- Synthesis of multi-band reflective polarizing metasurfaces using a generative adversarial networkScientific Reports, 2022
- Time Series Classification Based on Image Transformation Using Feature Fusion StrategyNeural Processing Letters, 2022
- Active modulation of electromagnetically induced transparency analogue in terahertz hybrid metal-graphene metamaterialsCarbon, 2018
- Active Control of Electromagnetically Induced Transparency Analog in Terahertz MEMS MetamaterialAdvanced Optical Materials, 2016
- Electromagnetically induced transparency in terahertz plasmonic metamaterials via dual excitation pathways of the dark modeApplied Physics Letters, 2012