volume | PIER Journals

Abstract

Full-wave electromagnetic simulation is computationally intensive during parametric antenna design and optimization. This study proposes a Support Vector Regression (SVR) based framework to predict the reflection coefficient of an Artificial Magnetic Conductor-Perfect Electric Conductor (AMC-PEC) metasurface antenna array in the X-band. The antenna comprises circular AMC cells and rectangular/grid PEC radiating elements arranged in a spatially optimized architecture. A dataset of 500 samples was generated using openEMS full-wave simulations, with antenna geometrical parameters as inputs and S₁₁ as the target response. An SVR model with a radial basis function kernel was trained and validated against simulations and measurements of a fabricated multilayer prototype. The predicted, simulated, and measured resonances occurred at approximately 9.8, 9.9, and 10.0 GHz, respectively, while measurements confirmed broadband impedance matching from 9.04 to 11.0 GHz. The SVR achieved a Mean Absolute Error (MAE) of 0.20 dB, Root Mean Square Error (RMSE) of 0.26 dB, and coefficient of determination (R²) of 0.998, outperforming Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) models trained on the same dataset. Predictions were generated in under one second, providing a speedup of approximately three orders of magnitude over full-wave simulation. The results demonstrate accurate and computationally efficient prediction for antenna design and optimization.

1. Iyer, Ashwin K., Andrea Alu, and Ariel Epstein, "Metamaterials and metasurfaces—historical context, recent advances, and future directions," IEEE Transactions on Antennas and Propagation, Vol. 68, No. 3, 1223-1231, March 2020.
doi:10.1109/tap.2020.2969732 Google Scholar

2. Holloway, C. L., E. F. Kuester, J. A. Gordon, J. O’Hara, J. Booth, and D. R. Smith, "An overview of the theory and applications of metasurfaces: The two-dimensional equivalents of metamaterials," IEEE Antennas and Propagation Magazine, Vol. 54, No. 2, 10-35, April 2012.
doi:10.1109/map.2012.6230714 Google Scholar

3. Yu, Nanfang, Patrice Genevet, Mikhail A. Kats, Francesco Aieta, Jean-Philippe Tetienne, Federico Capasso, and Zeno Gaburro, "Light propagation with phase discontinuities: Generalized laws of reflection and refraction," Science, Vol. 334, No. 6054, 333-337, October 2011.
doi:10.1126/science.1210713 Google Scholar

4. Cui, Tie Jun, Mei Qing Qi, Xiang Wan, Jie Zhao, and Qiang Cheng, "Coding metamaterials, digital metamaterials and programmable metamaterials," Light: Science & Applications, Vol. 3, No. 10, 218, October 2014.
doi:10.1038/lsa.2014.99 Google Scholar

5. Zou, Hanhua, Sanyou Zeng, Changhe Li, and Jingyu Ji, "A survey of machine learning and evolutionary computation for antenna modeling and optimization: Methods and challenges," Engineering Applications of Artificial Intelligence, Vol. 138, 109381, December 2024.
doi:10.1016/j.engappai.2024.109381 Google Scholar

6. Murugesan, Akila, Krishnasamy T. Selvan, Ashwin Iyer, Kumar Vaibhav Srivastava, and Arokiaswami Alphones, "A review of metasurface-assisted RCS reduction techniques," Progress In Electromagnetics Research B, Vol. 94, 75-103, 2021.
doi:10.2528/pierb21081401 Google Scholar

7. Prado, Daniel R., Jesus A. Lopez-Fernandez, Guillermo Barquero, Manuel Arrebola, and Fernando Las-Heras, "Fast and accurate modeling of dual-polarized reflectarray unit cells using support vector machines," IEEE Transactions on Antennas and Propagation, Vol. 66, No. 3, 1258-1270, March 2018.
doi:10.1109/tap.2018.2790044 Google Scholar

8. Reddy, Karnati Jagadish, Rayudu Vinay Kumar, Matta Venkata Durga Pavan Kumar, and B. Mamatha, "AI-driven metamaterial antenna design: A review," International Journal of Intelligent Systems and Applications in Engineering, Vol. 12, No. 4, 5571, 2024. Google Scholar

9. Akinsolu, Mobayode O., Keyur K. Mistry, Bo Liu, Pavlos I. Lazaridis, and Peter Excell, "Machine learning-assisted antenna design optimization: A review and the state-of-the-art," 2020 14th European Conference on Antennas and Propagation (EuCAP), 1-5, Copenhagen, Denmark, March 2020.
doi:10.23919/eucap48036.2020.9135936

10. El Misilmani, Hilal M., Tarek Naous, and Salwa K. Al Khatib, "A review on the design and optimization of antennas using machine learning algorithms and techniques," International Journal of RF and Microwave Computer-Aided Engineering, Vol. 30, No. 10, July 2020.
doi:10.1002/mmce.22356 Google Scholar

11. Patel, Shobhit K., Jaymit Surve, Vijay Katkar, and Juveriya Parmar, "Machine learning assisted metamaterial-based reconfigurable antenna for low-cost portable electronic devices," Scientific Reports, Vol. 12, Article number 12354, July 2022.
doi:10.1038/s41598-022-16678-2 Google Scholar

12. Dai, X. W., D. L. Mi, H. T. Wu, and Y. H. Zhang, "Design of compact patch antenna based on support vector regression," Radioengineering, Vol. 31, No. 3, 339-345, September 2022.
doi:10.13164/re.2022.0339 Google Scholar

13. Pedregosa, Fabian, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Édouard Duchesnay, "Scikit-learn: Machine learning in python," Journal of Machine Learning Research, Vol. 12, No. 85, 2825-2830, 2011. Google Scholar

14. Liebig, Thorsten, Andreas Rennings, Sebastian Held, and Daniel Erni, "OpenEMS --- a free and open source equivalent-circuit (EC) FDTD simulation platform supporting cylindrical coordinates suitable for the analysis of traveling wave MRI applications," International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, Vol. 26, No. 6, 680-696, December 2012.
doi:10.1002/jnm.1875 Google Scholar

15. Angiulli, G., M. Cacciola, and M. Versaci, "Microwave devices and antennas modelling by support vector regression machines," IEEE Transactions on Magnetics, Vol. 43, No. 4, 1589-1592, April 2007.
doi:10.1109/tmag.2007.892480 Google Scholar

16. Jacobs, J. P., "Efficient resonant frequency modeling for dual-band microstrip antennas by gaussian process regression," IEEE Antennas and Wireless Propagation Letters, Vol. 14, 337-341, 2015.
doi:10.1109/lawp.2014.2362937 Google Scholar

17. Wu, Yunqiu, Zongxi Tang, Yuehang Xu, Yunchuan Guo, and Biao Zhang, "Support vector regression for measuring electromagnetic parameters of magnetic thin-film materials," IEEE Transactions on Magnetics, Vol. 43, No. 12, 4071-4075, December 2007.
doi:10.1109/tmag.2007.908372 Google Scholar

18. Vapnik, V. N., Statistical Learning Theory, Wiley, New York, NY, USA, 1998.

19. Smola, Alex J. and Bernhard Schölkopf, "A tutorial on support vector regression," Statistics and Computing, Vol. 14, No. 3, 199-222, August 2004.
doi:10.1023/b:stco.0000035301.49549.88 Google Scholar

20. Koziel, Slawomir and Xin-She Yang, Computational Optimization, Methods and Algorithms, Springer Science & Business Media, 2011.

21. Jin, J.-M., Theory and Computation of Electromagnetic Fields, Wiley, Hoboken, NJ, USA, 2015.

22. Williams, C. K. I. and C. E. Rasmussen, Gaussian Processes for Machine Learning, MIT Press, Cambridge, MA, USA, 2006.

23. Ma, Wei, Zhaocheng Liu, Zhaxylyk A. Kudyshev, Alexandra Boltasseva, Wenshan Cai, and Yongmin Liu, "Deep learning for the design of photonic structures," Nature Photonics, Vol. 15, No. 2, 77-90, October 2020.
doi:10.1038/s41566-020-0685-y Google Scholar

24. Liu, Dianjing, Yixuan Tan, Erfan Khoram, and Zongfu Yu, "Training deep neural networks for the inverse design of nanophotonic structures," ACS Photonics, Vol. 5, No. 4, 1365-1369, February 2018.
doi:10.1021/acsphotonics.7b01377 Google Scholar

25. So, Sunae, Trevon Badloe, Jaebum Noh, Junsuk Rho, and Jorge Bravo‐Abad, "Deep learning enabled inverse design in nanophotonics," Nanophotonics, Vol. 9, No. 5, 1041-1057, February 2020.
doi:10.1515/nanoph-2019-0474 Google Scholar

26. Koziel, Slawomir, Anna Pietrenko-Dabrowska, and Stanislaw Szczepanski, "Multi-objective artificial-intelligence-based parameter tuning of antennas using variable-fidelity machine learning," Scientific Reports, Vol. 15, Article number 21693, July 2025.
doi:10.1038/s41598-025-05657-y Google Scholar

27. and Mersani, Ameni, Kawther Mekki, and Omran Ncibi, "AI-powered S11 prediction for a compact 2.4 GHz patch antenna," Indian Journal Of Science And Technology, Vol. 18, No. 33, 2715-2728, September 2025.
doi:10.17485/ijst/v18i33.1326 Google Scholar

28. Boulaich, Mohamed Hamza, Said Ohamouddou, Mohammed Ali Ennasar, and Abdellatif El Afia, "AI-assisted metasurface antennas design/optimization and performance enhancement techniques: A comprehensive survey," IEEE Access, Vol. 14, 29803-29835, 2026.
doi:10.1109/access.2026.3667812 Google Scholar

29. Islam, Md. Bipul, A. N. M. Shihab Uddin, Samiul Bashir, Pronab Kumar Paul, Md. Firoz Ahmed, and M. Hasnat Kabir, "Design optimization of a C/X-band metasurface–DGS microstrip antenna using machine learning," Physics Open, Vol. 27, 100419, May 2026.
doi:10.1016/j.physo.2026.100419 Google Scholar

30. Roy, Hrisikesh, Taimoor Khan, and Md. Maqbul, "Machine learning-based forward and inverse modeling framework for metasurface-aided antennas in 5G sub-6 GHz wireless power harvesting environments," AEU --- International Journal of Electronics and Communications, Vol. 213, 156361, July 2026.
doi:10.1016/j.aeue.2026.156361 Google Scholar

Mr. Deval Kumar

Dr. Somsing Rathod

Dr. Amit Kumar Singh