journal article·2024-04-01Open access

Deep-learning empowered unique and rapid optimization of meta-absorbers for solar thermophotovoltaics

Sadia Noureen, Sumbel Ijaz, Isma Javed, Humberto Cabrera, Marco Zennaro, Muhammad Zubair, Muhammad Qasim Mehmood, Yehia Massoud

Optical Materials Express· Volume 14· Issue 4

Abstract

Optical nano-structure designs usually employ computationally expensive and time-intensive electromagnetic (EM) simulations that call for resorting to modern-day data-oriented methods, making design robust and quicker. A unique dataset and hybrid image processing model combining a CNN with gated recurrent units is presented to foresee the EM absorption response of photonic nano-structures. An inverse model is also discussed to predict the optimum geometry and dimensions of meta-absorbers. Mean-squared error of the order of 10 −3 and an accuracy of 99% is achieved for trained models, and the average prediction time for the DL models is around 98% faster than that of simulations. This idea strengthens the proposition that efficient DL-based solutions can substitute the traditional methods for designing nano-optical structures.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Thermal Radiation and Cooling Technologies · Metamaterials and Metasurfaces Applications · Plasmonic and Surface Plasmon Research

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

Affiliations

The Abdus Salam International Centre for Theoretical Physics

King Abdullah University of Science and Technology (KAUST)

References (60)

Show source-provided references
1. Lv · Prog. Mater. Sci. · 2022 · 127 · 10094610.1016/j.pmatsci.2022.100946 ↗
2. Iyer · IEEE Trans. Antennas Propag. · 2020 · 68 · 122310.1109/TAP.2020.2969732 ↗
3. Naveed · Adv. Opt. Mater. · 2022 · 10 · 110.1002/adom.202200196 ↗
4. Li · eLight · 2022 · 2 · 710.1186/s43593-022-00013-3 ↗
5. Ijaz · Proc.SPIE · 2022 · 12004 · 5110.1117/12.2607885 ↗
6. Ijaz · Adv. Devices Instrum. · 2022 · 2022 · 110.34133/2022/9861078 ↗
7. Hong · Nanoscale Res. Lett. · 2022 · 17 · 4110.1186/s11671-022-03680-w ↗
8. Ni · eLight · 2022 · 2 · 2310.1186/s43593-022-00032-0 ↗
9. Chen · Light: Sci. Appl. · 2023 · 12 · 13610.1038/s41377-023-01177-4 ↗
10. Yim · eLight · 2022 · 2 · 1610.1186/s43593-022-00023-1 ↗
11. Krasnok · Mater. Today · 2018 · 21 · 810.1016/j.mattod.2017.06.007 ↗
12. Javed · ACS Appl. Mater. Interfaces · 2022 · 14 · 3601910.1021/acsami.2c07960 ↗
13. Li · Nanophotonics · 2018 · 7 · 98910.1515/nanoph-2017-0120 ↗
14. Sun · Front. Phys. · 2019 · 7 · 110.3389/fphy.2019.00181 ↗
15. Li · Light: Sci. Appl. · 2019 · 8 · 9710.1038/s41377-019-0209-z ↗
16. Zhang · Nanophotonics · 2020 · 10 · 25910.1515/nanoph-2020-0373 ↗
17. Rana · Nano Energy · 2021 · 80 · 10552010.1016/j.nanoen.2020.105520 ↗
18. Shockley · J. Appl. Phys. · 1961 · 32 · 51010.1063/1.1736034 ↗
19. Ijaz · Opt. Express · 2021 · 29 · 3153710.1364/OE.438899 ↗
20. Huang · Light: Sci. Appl. · 2021 · 10 · 2810.1038/s41377-021-00465-1 ↗
21. Luo · Sci. China Physics, Mech. Astron. · 2015 · 58 · 59420110.1007/s11433-015-5688-1 ↗
22. Bilal · Optik · 2020 · 216 · 16495810.1016/j.ijleo.2020.164958 ↗
23. Bilal · Sci. Rep. · 2020 · 10 · 1403510.1038/s41598-020-71032-8 ↗
24. Bilal · IEEE Access · 2021 · 9 · 567010.1109/ACCESS.2020.3048927 ↗
25. Naik · Adv. Mater. · 2013 · 25 · 326410.1002/adma.201205076 ↗
26. Naveed · Opt. Express · 2021 · 29 · 4291110.1364/OE.446423 ↗
27. Naveed · Appl. Opt. · 2021 · 60 · 916010.1364/AO.438237 ↗
28. Selmy · Emergent Mater. · 2018 · 1 · 18510.1007/s42247-018-0017-x ↗
29. Sell · Nano Lett. · 2017 · 17 · 375210.1021/acs.nanolett.7b01082 ↗
30. Chen · J. Opt. Soc. Am. B · 2024 · 41 · A16110.1364/JOSAB.506412 ↗
31. Pan · Photonics · 2023 · 10 · 85210.3390/photonics10070852 ↗
32. Molesky · Nat. Photonics · 2018 · 12 · 65910.1038/s41566-018-0246-9 ↗
33. Makarenko · Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. · 2022 · 2022 · 1268210.1109/CVPR52688.2022.01236 ↗
34. Nadell · Opt. Express · 2019 · 27 · 2752310.1364/OE.27.027523 ↗
35. Yang · Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. · 2022 · 2022 · 231310.1109/CVPR52688.2022.00236 ↗
36. So · Nanophotonics · 2020 · 9 · 104110.1515/nanoph-2019-0474 ↗
37. Xu · Photonics Res. · 2021 · 9 · B13510.1364/PRJ.417693 ↗
38. Wang · PhotoniX · 2021 · 2 · 2210.1186/s43074-021-00044-y ↗
39. Yiasemis · Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. · 2022 · 2022 · 722
40. Ijaz · Mater. Today Commun. · 2023 · 36 · 110.1016/j.mtcomm.2023.106377 ↗
41. Ignatov · Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) · 2019 · 11133 · 28810.1007/978-3-030-11021-5_19 ↗
42. Mall · Sci. Rep. · 2020 · 10 · 1942710.1038/s41598-020-76400-y ↗
43. Noureen · Nanoscale · 2022 · 14 · 1643610.1039/D2NR03644D ↗
44. Reducing complexity and data-set-size through physics inspired tandem neural network10.1109/ISCAS46773.2023.10181524 ↗
45. Liao · Opt. Mater. Express · 2022 · 12 · 75810.1364/OME.449152 ↗
46. Noureen · Opt. Mater. Express · 2021 · 11 · 317810.1364/OME.424826 ↗
47. An · Opt. Express · 2020 · 28 · 3193210.1364/OE.401960 ↗
48. So · Nanophotonics · 2019 · 8 · 125510.1515/nanoph-2019-0117 ↗
49. Saxena · ACM Computing Surveys · 2020 · 54 · 6310.1145/3446374 ↗
50. Zhaocheng · Nano Lett. · 2018 · 18 · 657010.1021/acs.nanolett.8b03171 ↗
51. Shelling Neto · Opt. Express · 2022 · 30 · 98610.1364/OE.446442 ↗
52. Tanriover · ACS Photonics · 2020 · 7 · 195710.1021/acsphotonics.0c00663 ↗
53. Johnson · Phys. Rev. B · 1974 · 9 · 505610.1103/PhysRevB.9.5056 ↗
54. Johnson · Phys. Rev. B · 1972 · 6 · 437010.1103/PhysRevB.6.4370 ↗
55. Werner · J. Phys. Chem. Ref. Data · 2009 · 38 · 101310.1063/1.3243762 ↗
56. Tao · Opt. Express · 2008 · 16 · 718110.1364/OE.16.007181 ↗
57. Hendrickson · Opt. Lett. · 2012 · 37 · 37110.1364/OL.37.000371 ↗
58. Zhang · Opt. Express · 2011 · 19 · 1522110.1364/OE.19.015221 ↗
59. Hedayati · Adv. Mater. · 2011 · 23 · 541010.1002/adma.201102646 ↗
60. Kats · Laser Photonics Rev. · 2016 · 10 · 73510.1002/lpor.201600098 ↗