journal article·2024-11-01Open access

Multi-receptive-field physics-informed neural network for complex electromagnetic media

Yinpeng Wang, Shihong Zhang

Optical Materials Express· Volume 14· Issue 11

Abstract

Acquiring the electromagnetic response of intricate media at the nanoscale constitutes a pivotal phase in the design intricacies of nanophotonic apparatuses. Conventional numerical algorithms often necessitate intricate and specialized treatments to accommodate the unique properties of the medium, coupled with substantial computational time and resource demands. In recent years, the advent of deep learning technology has heralded numerous advancements in the domain of computational electromagnetics, albeit with a scarcity of solvers tailored for versatile complex media. Consequently, this study introduces an innovative multi-receptive-field physics-informed neural network (MRF-PINN) designed to tackle nano optical scattering predicaments inherent in media exhibiting dispersion, inhomogeneity, anisotropy, nonlinearity, and chirality. This framework adeptly captures electromagnetic perturbations surrounding scatterers via variable-scale receptive fields, thereby enhancing prediction precision. Within the training regimen, a scale balancing algorithm is proposed to expedite network convergence. Empirical findings demonstrate that a fully trained MRF-PINN proficiently reconstructs electromagnetic field distributions within complex nanomaterials within a mere tens of milliseconds of inference time. Such quasi real-time capabilities herald a novel approach to supplant the arduous forward calculation processes inherent in nanomaterial design workflows.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Neural Networks and Applications · Neural Networks and Reservoir Computing · Advanced Optical Sensing Technologies

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

Affiliations

Beihang University

References (38)

Show source-provided references
1. Prasad · 2004
2. Giannini · Chem. Rev. · 2011 · 111 · 388810.1021/cr1002672 ↗
3. Cui · J. Phys. Photonics · 2024 · 6 · 03250210.1088/2515-7647/ad1a3b ↗
4. Kuznetsov · ACS Photonics · 2024 · 11 · 81610.1021/acsphotonics.3c00457 ↗
5. Joannopoulos · Nature · 1997 · 386 · 14310.1038/386143a0 ↗
6. Altug · Nat. Nanotechnol. · 2022 · 17 · 510.1038/s41565-021-01045-5 ↗
7. Teixeira · Nat. Rev. Methods Primers · 2023 · 3 · 7510.1038/s43586-023-00257-4 ↗
8. Jin · 2014
9. Gibson · 2022
10. Teixeira · IEEE Trans. Antennas Propag. · 2008 · 56 · 215010.1109/TAP.2008.926767 ↗
11. Rekanos · IEEE Trans. Antennas Propag. · 2010 · 58 · 366610.1109/TAP.2010.2071365 ↗
12. Bui · IEEE Trans. Microwave Theory Tech. · 1991 · 39 · 116510.1109/22.85384 ↗
13. Sullivan · IEEE Trans. Antennas Propag. · 1992 · 40 · 122310.1109/8.182455 ↗
14. Levy · Phys. Rev. B · 1997 · 56 · 803510.1103/PhysRevB.56.8035 ↗
15. Stroud · Superlattices Microstruct. · 1998 · 23 · 56710.1006/spmi.1997.0524 ↗
16. Konrad · IEEE Trans. Microwave Theory Tech. · 1976 · 24 · 55310.1109/TMTT.1976.1128908 ↗
17. Garcia · IEEE Trans. Microwave Theory Tech. · 1996 · 44 · 219510.1109/22.556447 ↗
18. Tran · Opt. Lett. · 1996 · 21 · 113810.1364/OL.21.001138 ↗
19. Sullivan · IEEE Trans. Microwave Theory Tech. · 1995 · 43 · 67610.1109/22.372115 ↗
20. Bohren · J. Colloid Interface Sci. · 1978 · 66 · 10510.1016/0021-9797(78)90189-3 ↗
21. Wang · 2023
22. Wang · IEEE J. Multiscale Multiphys. Comput. Tech. · 2021 · 6 · 10010.1109/JMMCT.2021.3106539 ↗
23. Wang · Int. J. Heat Mass Transfer · 2022 · 186 · 12244410.1016/j.ijheatmasstransfer.2021.122444 ↗
24. Wang · Case Stud. Therm. Eng. · 2022 · 33 · 10192710.1016/j.csite.2022.101927 ↗
25. Sun · Int. J. Thermofluids · 2024 · 23 · 10072610.1016/j.ijft.2024.100726 ↗
26. Wang · Adv. Theory Simul. · 2022 · 5 · 220040910.1002/adts.202200409 ↗
27. Lupoiu · 2023 · 225
28. Ren · 2022
29. Qi · IEEE J. Multiscale Multiphys. Comput. Tech. · 2020 · 5 · 8310.1109/JMMCT.2020.2995811 ↗
30. Li · IEEE Access · 2020 · 8 · 13998310.1109/ACCESS.2020.3012132 ↗
31. Zhai · Antennas Wirel. Propag. Lett. · 2023 · 22 · 252210.1109/LAWP.2023.3294499 ↗
32. Raissi · J. Comput. Phys. · 2019 · 378 · 68610.1016/j.jcp.2018.10.045 ↗
33. Karniadakis · Nat. Rev. Phys. · 2021 · 3 · 42210.1038/s42254-021-00314-5 ↗
34. Zhang · IEEE J. Multiscale Multiphys. Comput. Tech. · 2021 · 6 · 3510.1109/JMMCT.2021.3057793 ↗
35. Hu · IEEE Trans. Antennas Propag. · 2022 · 70 · 76710.1109/TAP.2021.3098585 ↗
36. Ma · IEEE Trans. Antennas Propag. · 2021 · 69 · 219410.1109/TAP.2020.3026447 ↗
37. Kuhn · APL Photonics · 2023 · 8 · 03610910.1063/5.0139004 ↗
38. Yao · Pattern Recognit. · 2022 · 123 · 10836910.1016/j.patcog.2021.108369 ↗