journal article·2026-08-01Open access

Machine learning-assisted design and analysis of a broadband metamaterial absorber

Robiul Hasan, Imtiaz Ahmed, Md. Eyasin Ali

Optical Materials Express· Volume 16· Issue 8

Abstract

In this paper a near perfect broadband metamaterial absorber (MA) is proposed that uses a vanadium oxide(VO 2 ) layer on top, a TOPAS layer in middle and a thin gold layer on bottom. The absorber achieves absorption over 90% for a bandwidth of 4.36 THz from 3.88 THz to 8.23 THz and an absorption over 99% from 3.95 THz to 6.8 THz. The metasurface consists of an outer square ring resonator and an inner square split ring resonator which enables the generation of multiple resonance modes. The structure is optimized to achieve the highest bandwidth while keeping VO 2 in the conduction state. The interference cancelation and impedance matching theory are used to explain the physical mechanism of the absorber. The modulation depth, extinction ratio, electric and magnetic field distribution, and surface current density are also analyzed. Absorption can be tuned from 2% to more than 99% by changing the conductivity of the VO 2 from 200 S/m to 2 × 10 5 S/m using different operating temperatures. The designed absorber is polarization insensitive and demonstrates wide angle absorption for TE and TM modes. Machine learning was implemented using six regression models to predict absorption for different frequencies and structure parameters. Among them, the XGBoost regression model demonstrated the best performance, with a mean R 2 of 0.9959 ± 0.001 and a mean RMSE of 0.0236 ± 0.003 for a 10-fold group cross validation and a confidence interval of 95%. The robust performance, easy fabrication, and flexibility in design make the proposed absorber suitable for many real world applications.
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.

References (50)

Show source-provided references
1. Siegel · IEEE Trans. Microwave Theory Tech. · 2002 · 50 · 91010.1109/22.989974 ↗
2. Tonouchi · Nat. Photonics · 2007 · 1 · 9710.1038/nphoton.2007.3 ↗
3. Mittleman · J. Appl. Phys. · 2017 · 122 · 23090110.1063/1.5007683 ↗
4. Landy · Phys. Rev. Lett. · 2008 · 100 · 20740210.1103/PhysRevLett.100.207402 ↗
5. Watts · Adv. Mater. · 2012 · 24 · OP9810.1007/978-3-031-03765-8 ↗
6. Ding · Rep. Prog. Phys. · 2018 · 81 · 02640110.1088/1361-6633/aa8732 ↗
7. Ali · IEEE Trans. Plasma Sci. · 2025 · 53 · 214010.1109/TPS.2025.3586455 ↗
8. Zou · Materials · 2023 · 16 · 471910.3390/ma16134719 ↗
9. Wang · Nanomaterials · 2023 · 13 · 47010.3390/nano13030470 ↗
10. Liu · Nature · 2012 · 487 · 34510.1038/nature11231 ↗
11. Driscoll · Science · 2009 · 325 · 151810.1126/science.1176580 ↗
12. Shao · J. Appl. Phys. · 2015 · 117 · 06310110.1063/1.4905081 ↗
13. Mou · Sci. Rep. · 2022 · 12 · 250110.1038/s41598-022-04772-4 ↗
14. Ali · Phys. Scr. · 2024 · 99 · 01550110.1088/1402-4896/ad0fcc ↗
15. Zhang · Sci. Rep. · 2025 · 15 · 1026810.1038/s41598-025-95566-x ↗
16. Wei · Phys. Scr. · 2025 · 100 · 08556510.1088/1402-4896/adf676 ↗
17. Sun · Opt. Commun. · 2023 · 541 · 12956310.1016/j.optcom.2023.129602 ↗
18. Jain · Sci. Rep. · 2023 · 13 · 179210.1038/s41598-023-29024-x ↗
19. Soni · ACS Applied Optical Materials · 2023 · 1 · 167910.1021/acsaom.3c00246 ↗
20. Hakim · Journal of Macromolecular Science Part B · 2023 · 62 · 110.1016/j.matchemphys.2023.128180 ↗
21. Jain · Alexandria Engineering Journal · 2024 · 103 · 5110.1016/j.aej.2024.05.111 ↗
22. Chouhan · J. Lightwave Technol. · 2024 · 42 · 654710.1109/JLT.2024.3353330 ↗
24. Huang · Photonics · 2025 · 13 · 15710.3390/photonics13010031 ↗
25. Huang · Nano Lett. · 2023 · 23 · 1099110.1021/acs.nanolett.3c03258 ↗
26. Deng · Nano Lett. · 2024 · 24 · 1464110.1021/acs.nanolett.4c03695 ↗
27. Deng · Nat. Commun. · 2024 · 15 · 223710.1038/s41467-024-46537-9 ↗
28. You · Laser Photonics Rev. · 2025 · 19 · 240101110.1002/lpor.202401011 ↗
29. Rong · Opt. Laser Technol. · 2026 · 200 · 11518510.1016/j.optlastec.2026.115185 ↗
30. Zheng · Opto-Electron. Adv. · 2025 · 8 · 24015910.29026/oea.2025.240159 ↗
31. Li · Opto-Electron. Sci. · 2025 · 4 · 24002510.29026/oes.2025.240025 ↗
32. Liu · Opto-Electron. Technol. · 2026 · 2 · 26000110.29026/oet.2026.260001 ↗
33. Zhu · J. Opt. Soc. Am. B · 2012 · 29 · 237310.1364/JOSAB.29.002373 ↗
34. Ali · IEEE Trans. Plasma Sci. · 2024 · 52 · 54510.1109/TPS.2023.3342115 ↗
35. Zhang · Micromachines · 2022 · 13 · 66910.3390/mi13050669 ↗
36. Ali · IEEE Trans. Plasma Sci. · 2025 · 53 · 397410.1109/TPS.2025.3625419 ↗
37. Li · Chin. Phys. B · 2021 · 30 · 09810210.1088/1674-1056/abfb57 ↗
38. Tang · RSC Adv. · 2018 · 8 · 4223310.1039/C8RA08008A ↗
39. Zhao · Results Phys. · 2021 · 28 · 10462810.1016/j.rinp.2021.104628 ↗
40. Wang · J. Lightwave Technol. · 2014 · 32 · 229310.1109/JLT.2014.2322860 ↗
41. Kim · Appl. Phys. Lett. · 2007 · 90 · 02351510.1063/1.2431456 ↗
42. Zhu · Opt. Express · 2020 · 28 · 3862610.1364/OE.414039 ↗
43. Ahmed · Sci. Rep. · 2025 · 15 · 4426310.1038/s41598-025-27928-4 ↗
44. Huang · Opt. Express · 2020 · 28 · 701810.1364/OE.387156 ↗
45. Liu · Photonics · 2024 · 11 · 57810.3390/photonics11060578 ↗
46. Jyoti · IEEE Access · 2025 · 13 · 19545010.1109/ACCESS.2025.3631711 ↗
47. Ri · AIP Adv. · 2024 · 14 · 05530110.1063/5.0203342 ↗
48. Zhang · AIP Adv. · 2024 · 14 · 10500710.1063/5.0227652 ↗
49. Xiong · J. Mater. Chem. C · 2025 · 13 · 1569810.1039/D5TC01763G ↗
50. Ge · Opt. Express · 2025 · 33 · 393010.1364/OE.548058 ↗