journal article·2025-11-01Open access

Inverse metasurface design enabling arbitrary spectral and polarization control

Md Imran Hossain, Linzhi Yu, Humeyra Caglayan

Optical Materials Express· Volume 15· Issue 11

Abstract

Metasurface has unusual light-matter interactions and possesses a distinctive capacity to control the electromagnetic wave’s amplitude, phase, and polarization. It is challenging to come up with a well-designed metasurface that supports the desired optical response. The conventional design approach requires extensive parameter sweeps, trial-and-error in design space, and hours of computational efforts and resources. Deep learning has recently gained attention in optics and photonics and is increasingly being applied to solve design and optimization problems. In this work, a framework consisting of a conditional generative adversarial network and a residual network-based neural network simulator is presented that has been trained to predict the geometry and transmission spectra of the metasurfaces within a moment. The framework takes a set of transmitted complex electric fields. It can generate a potential candidate metasurface unit cell corresponding to the user-defined spectra. The simulator network can predict the transmission spectra of metasurfaces with complex shapes and diverse geometries. The framework has the potential to significantly accelerate the design and simulation of metasurfaces, with promising applications in spectral filtering, polarization conversion, and beam shaping in micro and nanoscale devices.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Metamaterials and Metasurfaces Applications · Advanced Antenna and Metasurface Technologies · Antenna Design and Analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Tampere University

Funding

Research Council of Finland · Horizon 2020 Framework Programme

References (52)

Show source-provided references
1. Walia · Appl. Phys. Rev. · 2015 · 2 · 01130310.1063/1.4913751 ↗
2. Chen · Nat. Rev. Mater. · 2020 · 5 · 60410.1038/s41578-020-0203-3 ↗
3. Yu · Nat. Mater. · 2014 · 13 · 13910.1038/nmat3839 ↗
4. Atalay Appak · Nanophotonics · 2023 · 12 · 362310.1515/nanoph-2023-0321 ↗
5. Deng · Nat. Commun. · 2024 · 15 · 223710.1038/s41467-024-46537-9 ↗
7. Ni · Nat. Commun. · 2013 · 4 · 280710.1038/ncomms3807 ↗
8. Liu · Opt. Lett. · 2015 · 40 · 318510.1364/OL.40.003185 ↗
9. Li · Opt. Mater. Express · 2024 · 14 · 261210.1364/OME.539800 ↗
10. Ahmad · Phys. Scr. · 2024 · 99 · 03590810.1088/1402-4896/ad2141 ↗
11. Ahmad · Opt. Continu. · 2023 · 2 · 124210.1364/OPTCON.487078 ↗
12. He · Opt. Lett. · 2022 · 47 · 247810.1364/OL.456910 ↗
13. Roy · Opt. Mater. Express · 2024 · 14 · 123910.1364/OME.520736 ↗
14. Yu · Nano Lett. · 2025 · 25 · 741910.1021/acs.nanolett.5c00873 ↗
15. Conteduca · Nat. Commun. · 2021 · 12 · 329310.1038/s41467-021-23357-9 ↗
16. Yu · Nano Lett. · 2025 · 25 · 1169610.1021/acs.nanolett.5c02789 ↗
17. Deng · Nano Lett. · 2024 · 24 · 1464110.1021/acs.nanolett.4c03695 ↗
18. Huang · Sci. China Phys. Mech. Astron. · 2025 · 68 · 27420110.1007/s11433-025-2669-5 ↗
19. Chen · Rep. Prog. Phys. · 2016 · 79 · 07640110.1088/0034-4885/79/7/076401 ↗
20. Dhama · Nat. Commun. · 2022 · 13 · 311410.1038/s41467-022-30750-5 ↗
21. Hsiao · Small Methods · 2017 · 1 · 160006410.1002/smtd.201600064 ↗
22. Shuvo · Sci. Rep. · 2022 · 12 · 485710.1038/s41598-022-08829-2 ↗
23. Dainese · Light: Sci. Appl. · 2024 · 13 · 30010.1038/s41377-024-01629-5 ↗
24. Liu · Adv. Mater. · 2020 · 32 · 190479010.1002/adma.201904790 ↗
25. Chen · Chem. Rev. · 2022 · 122 · 1535610.1021/acs.chemrev.2c00012 ↗
26. Yao · Nanophotonics · 2019 · 8 · 33910.1515/nanoph-2018-0183 ↗
27. Kuster · Nanophotonics · 2025 · 14 · 141510.1515/nanoph-2025-0067 ↗
28. Kiarashinejad · npj Comput. Mater. · 2020 · 6 · 1210.1038/s41524-020-0276-y ↗
29. An · Opt. Express · 2020 · 28 · 3193210.1364/OE.401960 ↗
30. O’shea · 201510.48550/arXiv.1511.08458 ↗
31. Qiu · Adv. Sci. · 2019 · 6 · 190012810.1002/advs.201900128 ↗
32. Nadell · Opt. Express · 2019 · 27 · 2752310.1364/OE.27.027523 ↗
33. Teng · Opt. Laser Technol. · 2023 · 160 · 10905810.1016/j.optlastec.2022.109058 ↗
34. Liu · IEEE J. Emerg. Sel. Topics Circuits Syst. · 2020 · 10 · 12610.1109/JETCAS.2020.2970080 ↗
35. Pu · Advances in Neural Information Processing Systems · 2016 · 29 · 236010.5555/3157096.3157360 ↗
36. Ma · Nat. Photonics · 2021 · 15 · 7710.1038/s41566-020-0685-y ↗
37. Jiang · Nat. Rev. Mater. · 2021 · 6 · 67910.1038/s41578-020-00260-1 ↗
39. Palik · 1998
40. LeCun · Nature · 2015 · 521 · 43610.1038/nature14539 ↗
41. Deng · IEEE Signal Process. Mag. · 2012 · 29 · 14110.1109/MSP.2012.2211477 ↗
42. Kunz · 1993
43. Wang · IEEE Signal Process. Mag. · 2009 · 26 · 9810.1109/MSP.2008.930649 ↗
44. Gulrajani · Advances in Neural Information Processing Systems · 2017 · 30 · 576910.5555/3295222.3295327 ↗
45. Fathnan · J. Phys. D: Appl. Phys. · 2020 · 53 · 49530410.1088/1361-6463/abb390 ↗
46. Ding · Sci. Rep. · 2016 · 6 · 3944510.1038/srep39445 ↗
47. Schulz · Appl. Phys. Lett. · 2024 · 124 · 26070110.1063/5.0204694 ↗
48. Liu · Opt. Express · 2020 · 28 · 482510.1364/OE.387504 ↗
49. Wang · Opt. Express · 2023 · 31 · 3776310.1364/OE.503139 ↗
50. Kang · Opt. Lett. · 2024 · 49 · 392210.1364/OL.527384 ↗
51. Singh · Digital Discovery · 2024 · 3 · 161210.1039/D4DD00107A ↗
52. Hossain M. I. Yu L. Caglayan H. , “ Inverse Design of Metasurfaces CGAN ,” Github , 2024 , https://github.com/metaphotonics/Inverse-metasurface-design-CGAN