EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep learning-based inverse design of broadband metasurface polarization converter

Yue Zhou, Tianyou Lai, Xiaodong He

AIP Advances · 01.07.2025 · 15 (7)

DOI: 10.1063/5.0281453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 23.07.2025. Verfasst von Yue Zhou und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Science and Technology Support Program of Gansu Province, Gansu Provincial IC Manufacturing Materials Innovation Consortium Project 2022.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning offers promising new methods for the design and optimization of electromagnetic metasurfaces. In this study, we propose a hybrid deep learning model that integrates a Convolutional Neural Network (CNN) with a Transformer architecture (CNN-Transformer) for the inverse design of broadband polarization converters, using polarization conversion ratio spectra as input. To enhance the robustness and generalization capability of the model under limited data conditions, Gaussian noise is incorporated into the training data as a data augmentation strategy within a few-shot learning framework. In comparison with a conventional Multilayer Perceptron (MLP), the CNN-Transformer model achieves markedly superior performance, attaining an average mean squared error of 0.003 31 and significantly outperforming the MLP baseline. Utilizing the structural parameters predicted by the model, a broadband linear polarization converter was designed and fabricated, demonstrating excellent polarization conversion efficiency across the 4–16 GHz frequency range. Both the simulation and experimental results confirmed the accuracy and effectiveness of the proposed method for structural parameter prediction. This study substantially streamlines the design process of electromagnetic metasurfaces, delivers high design precision and robust performance, and further highlights the potential of deep learning in advancing the development of complex metasurface devices.

Förderung

  • Science and Technology Support Program of Gansu Province
  • Gansu Provincial IC Manufacturing Materials Innovation Consortium Project 2022

Zitieren

APA

Zhou, Y., Lai, T., & He, X. (2025). Deep learning-based inverse design of broadband metasurface polarization converter. AIP Advances, 15(7). https://doi.org/10.1063/5.0281453

Vancouver

Zhou Y, Lai T, He X. Deep learning-based inverse design of broadband metasurface polarization converter. AIP Advances. 2025;15(7). doi:10.1063/5.0281453

BibTeX
@article{Zhou2025,
  author = {Zhou, Yue and Lai, Tianyou and He, Xiaodong},
  title = {Deep learning-based inverse design of broadband metasurface polarization converter},
  journal = {AIP Advances},
  year = {2025},
  volume = {15},
  number = {7},
  doi = {10.1063/5.0281453}
}
Kostenlos starten →