General Inverse Design of Layered Thin-Film Materials with Convolutional Neural Networks
Source abstract
Abstract
The design of metamaterials which support unique optical responses is the basis for most thin-film nanophotonic applications. In practice, this inverse design (ID) problem can be difficult to solve systematically due to the large design parameter space associated with general multilayered systems. We apply convolutional neural networks, a subset of deep machine learning, as a tool to solve this ID problem for metamaterials composed of stacks of thin films. We demonstrate the remarkable ability of neural networks to probe the large global design space (up to 1012 possible parameter combinations) and resolve all relationships between the metamaterial structure and corresponding ellipsometric and reflectance/transmittance spectra. The applicability of the approach is further expanded to include the ID of synthetic engineered spectra in general design scenarios. Furthermore, this approach is compared with traditional optimization methods. We find an increase in the relative optimization efficiency of the networks with the increase in the total layer number, revealing the advantage of the machine learning approach in many-layered systems where traditional methods become impractical.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Photonic Crystals and Applications · Metamaterials and Metasurfaces Applications · Optical Coatings and Gratings
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physics, Case Western Reserve University, 2076 Adelbert Road, Cleveland, Ohio 44106, United States
CNR NANOTEC, Istituto di Nanotecnologia and Department of Physics, University of Calabria, Rende, Calabria 87036, Italy
Funding
Division of Chemistry · Research Cluster on Surfaces in Advanced Materials
References (51)
Show source-provided references
1. 10.1021/acs.nanolett.8b0484110.1021/acs.nanolett.8b04841 ↗
2. 10.1039/c0cs00184h10.1039/c0cs00184h ↗
3. 10.1038/nmat383910.1038/nmat3839 ↗
4. 10.1038/s41565-020-00841-910.1038/s41565-020-00841-9 ↗
5. Sreekanth K. V. · 2019
6. 10.1515/nanoph-2018-018310.1515/nanoph-2018-0183 ↗
7. 10.1038/s41566-018-0246-910.1038/s41566-018-0246-9 ↗
8. 10.1126/sciadv.aar420610.1126/sciadv.aar4206 ↗
9. 10.1038/s42005-018-0058-810.1038/s42005-018-0058-8 ↗
10. 10.1021/acsphotonics.7b0137710.1021/acsphotonics.7b01377 ↗
11. 10.1002/lpor.20150012210.1002/lpor.201500122 ↗
12. 10.1038/s41377-019-0192-410.1038/s41377-019-0192-4 ↗
13. 10.1038/s41566-020-0685-y10.1038/s41566-020-0685-y ↗
14. 10.1515/nanoph-2019-047410.1515/nanoph-2019-0474 ↗
15. 10.1016/0893-6080(89)90020-810.1016/0893-6080(89)90020-8 ↗
16. 10.1007/s12541-019-00260-410.1007/s12541-019-00260-4 ↗
17. 10.1038/s41598-020-69754-w10.1038/s41598-020-69754-w ↗
18. 10.1038/s41598-019-41316-910.1038/s41598-019-41316-9 ↗
19. 10.1021/acsphotonics.8b0152610.1021/acsphotonics.8b01526 ↗
20. 10.1002/advs.20200292310.1002/advs.202002923 ↗
21. 10.1038/s41377-018-0060-710.1038/s41377-018-0060-7 ↗
22. 10.1021/acs.nanolett.9b0185710.1021/acs.nanolett.9b01857 ↗
23. 10.1515/nanoph-2020-019710.1515/nanoph-2020-0197 ↗
24. 10.1021/acsnano.8b0356910.1021/acsnano.8b03569 ↗
25. 10.1364/oe.27.02752310.1364/oe.27.027523 ↗
26. 10.1364/oe.27.0a103010.1364/oe.27.0a1030 ↗
27. 10.1109/jlt.2021.305008310.1109/jlt.2021.3050083 ↗
28. 10.1002/adom.20210054810.1002/adom.202100548 ↗
29. 10.35848/1882-0786/ab7cf110.35848/1882-0786/ab7cf1 ↗
30. Kim, S.; Lu, P. Y.; Loh, C.; Smith, J.; Snoek, J.; Soljačić, M. Scalable and Flexible Deep Bayesian Optimization with Auxiliary Information for Scientific Problems, 2021. arXiv:2104.11667.
31. 10.1364/ome.9.00385710.1364/ome.9.003857 ↗
32. 10.1364/ol.38740410.1364/ol.387404 ↗
33. 10.1038/s41378-019-0069-y10.1038/s41378-019-0069-y ↗
34. 10.1364/oe.26.03270410.1364/oe.26.032704 ↗
35. 10.1515/nanoph-2019-011710.1515/nanoph-2019-0117 ↗
36. 10.1016/j.optcom.2020.12664110.1016/j.optcom.2020.126641 ↗
37. 10.1109/72.55419510.1109/72.554195 ↗
38. 10.1145/306538610.1145/3065386 ↗
39. 10.1016/j.neucom.2016.12.03810.1016/j.neucom.2016.12.038 ↗
40. 10.1038/nature1453910.1038/nature14539 ↗
41. 10.1038/s41467-018-04316-310.1038/s41467-018-04316-3 ↗
42. 10.1146/annurev.ms.11.080181.00052510.1146/annurev.ms.11.080181.000525 ↗
43. 10.1364/josaa.1.00074210.1364/josaa.1.000742 ↗
44. 10.1364/ao.51.00827710.1364/ao.51.008277 ↗
45. 10.1023/a:100820282132810.1023/a:1008202821328 ↗
46. 10.1063/1.327227410.1063/1.3272274 ↗
47. 10.1364/ao.35.00549310.1364/ao.35.005493 ↗
48. 10.1364/ao.46.00070410.1364/ao.46.000704 ↗
49. 10.1364/ao.35.00548410.1364/ao.35.005484 ↗
50. 10.1007/s10462-020-09825-610.1007/s10462-020-09825-6 ↗
51. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016; pp 770–778.10.1109/CVPR.2016.90 ↗