journal article·2022-10-01Open access

Inverse design paradigm for fast and accurate prediction of a functional metasurface via deep convolutional neural networks

Xudong Du, Chengan Zhou, Hongbai Bai, Xingxing Liu

Optical Materials Express· Volume 12· Issue 10

Abstract

Data-driven deep learning frameworks have significantly advanced the development of modern machine learning, and after achieving great success in the field of image, speech, and video recognition and processing, they have also begun to permeate other disciplines such as physics, chemistry, and the discovery of new drugs and new materials. Our work proposes a deep learning-based model consisting of two parts: a forward simulation network that contains a transposed convolutional network, up and down sampling blocks and dense layers can rapidly predict optical responses from metasurface structures, and an inverse design network that contains convolutional neural networks and dense layers can automatically construct metasurface based on the input optical responses. Our model assists in discovering the complex and non-intuitive relationship between the moth-eye metasurface and optical responses, and designs a metasurface with excellent optical properties (ultra-broadband anti-reflection or nonlinear function of reflectivity), while avoiding traditional time-consuming case-by-case numerical simulations in the metasurface design. This work provides a fast, practical, and robust method to study complex light-matter interactions and to accelerate the demand-based design of nanophotonic devices, opening a new avenue for the development of real nanophotonic applications.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Metamaterials and Metasurfaces Applications · Animal Vocal Communication and Behavior · Photonic Crystals and Applications

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

References (29)

Show source-provided references
1. Srinivasarao · Chem. Rev. · 1999 · 99 · 193510.1021/cr970080y ↗
2. Huang · Nat. Nanotechnol. · 2007 · 2 · 77010.1038/nnano.2007.389 ↗
3. Jeong · Nano Lett. · 2012 · 12 · 297110.1021/nl300713x ↗
4. Ji · Nanoscale · 2012 · 4 · 460310.1039/c2nr30787a ↗
5. Huntington · Nano Lett. · 2014 · 14 · 719510.1021/nl5040573 ↗
6. Andkjaer · J. Opt. Soc. Am. B · 2010 · 27 · 182810.1364/JOSAB.27.001828 ↗
7. Forestiere · Opt. Lett. · 2010 · 35 · 13310.1364/OL.35.000133 ↗
8. LeCun · Nature · 2015 · 521 · 43610.1038/nature14539 ↗
9. Hinton · IEEE Signal Process. Mag. · 2012 · 29 · 8210.1109/MSP.2012.2205597 ↗
10. Krizhevsky · Commun. ACM · 2012 · 60 · 8410.1145/3065386 ↗
11. Silver · Nature · 2016 · 529 · 48410.1038/nature16961 ↗
12. Ramprasad · npj Comput. Mater. · 2017 · 3 · 5410.1038/s41524-017-0056-5 ↗
13. Baldi · Nat. Commun. · 2014 · 5 · 430810.1038/ncomms5308 ↗
14. Carleo · Science · 2017 · 355 · 60210.1126/science.aag2302 ↗
15. Carrasquilla · Nat. Phys. · 2017 · 13 · 43110.1038/nphys4035 ↗
16. Rivenson · Optica · 2017 · 4 · 143710.1364/OPTICA.4.001437 ↗
17. Capizzi · Micromachines · 2016 · 7 · 11010.3390/mi7070110 ↗
18. Peurifoy · Sci. Adv. · 2018 · 4 · eaar420610.1126/sciadv.aar4206 ↗
19. Liu · ACS Photonics · 2018 · 5 · 136510.1021/acsphotonics.7b01377 ↗
20. Malkiel · Light: Sci. Appl. · 2018 · 7 · 6010.1038/s41377-018-0060-7 ↗
21. Asano · Opt. Express · 2018 · 26 · 3270410.1364/OE.26.032704 ↗
22. Tahersima · Sci. Rep. · 2019 · 9 · 136810.1038/s41598-018-37952-2 ↗
23. Pilozzi · Commun. Phys. · 2018 · 1 · 5710.1038/s42005-018-0058-8 ↗
24. Badloe · Phys. Chem. Chem. Phys. · 2020 · 22 · 233710.1039/C9CP05621A ↗
25. Ma · ACS Nano · 2018 · 12 · 632610.1021/acsnano.8b03569 ↗
26. Palik · 1998 · 3
27. Wang · IEEE Trans. Pattern Anal. Mach. Intell. · 2021 · 43 · 336510.1109/TPAMI.2020.2982166 ↗
28. Dong · IEEE Trans. Pattern Anal. Mach. Intell. · 2015 · 38 · 29510.1109/TPAMI.2015.2439281 ↗
29. Cho · J. Inf. Disp. · 2017 · 18 · 13710.1080/15980316.2017.1325017 ↗