Deep Learning: a New Tool for Photonic Nanostructure Design

Overview

Journal Nanoscale Adv

Publisher Royal Society of Chemistry

Specialty Biotechnology

Date 2022 Sep 22

PMID 36133043

Authors

Ravi S Hegde

Affiliations

Soon will be listed here.

Abstract

Early results have shown the potential of Deep Learning (DL) to disrupt the fields of optical inverse-design, particularly, the inverse design of nanostructures. In the last three years, the complexity of the optical nanostructure being designed and the sophistication of the employed DL methodology have steadily increased. This topical review comprehensively surveys DL based design examples from the nanophotonics literature. Notwithstanding the early success of this approach, its limitations, range of validity and its place among established design techniques remain to be assessed. The review also provides a perspective on the limitations of this approach and emerging research directions. It is hoped that this topical review may help readers to identify unaddressed problems, to choose an initial setup for a specific problem, and, to identify means to improve the performance of existing DL based workflows.

Citing Articles

Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies.

Chapagain A, Abuoliem D, Cho I Nanomaterials (Basel). 2025; 15(1.

PMID: 39791786 PMC: 11722515. DOI: 10.3390/nano15010027.

Advancing statistical learning and artificial intelligence in nanophotonics inverse design.

Wang Q, Makarenko M, Burguete Lopez A, Getman F, Fratalocchi A Nanophotonics. 2024; 11(11):2483-2505.

PMID: 39635678 PMC: 11502023. DOI: 10.1515/nanoph-2021-0660.

Deep learning in light-matter interactions.

Midtvedt D, Mylnikov V, Stilgoe A, Kall M, Rubinsztein-Dunlop H, Volpe G Nanophotonics. 2024; 11(14):3189-3214.

PMID: 39635557 PMC: 11501725. DOI: 10.1515/nanoph-2022-0197.

A newcomer's guide to deep learning for inverse design in nano-photonics.

Khaireh-Walieh A, Langevin D, Bennet P, Teytaud O, Moreau A, Wiecha P Nanophotonics. 2024; 12(24):4387-4414.

PMID: 39634708 PMC: 11501815. DOI: 10.1515/nanoph-2023-0527.

Inverse design of structural color: finding multiple solutions conditional generative adversarial networks.

Dai P, Sun K, Yan X, Muskens O, de Groot C, Zhu X Nanophotonics. 2024; 11(13):3057-3069.

PMID: 39634659 PMC: 11501759. DOI: 10.1515/nanoph-2022-0095.

References

Mesch M, Weiss T, Schaferling M, Hentschel M, Hegde R, Giessen H . Highly Sensitive Refractive Index Sensors with Plasmonic Nanoantennas-Utilization of Optimal Spectral Detuning of Fano Resonances. ACS Sens. 2018; 3(5):960-966. DOI: 10.1021/acssensors.8b00003. View

Melati D, Grinberg Y, Kamandar Dezfouli M, Janz S, Cheben P, Schmid J . Mapping the global design space of nanophotonic components using machine learning pattern recognition. Nat Commun. 2019; 10(1):4775. PMC: 6803653. DOI: 10.1038/s41467-019-12698-1. View

Genevet P, Capasso F . Holographic optical metasurfaces: a review of current progress. Rep Prog Phys. 2015; 78(2):024401. DOI: 10.1088/0034-4885/78/2/024401. View

Jiang J, Sell D, Hoyer S, Hickey J, Yang J, Fan J . Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks. ACS Nano. 2019; 13(8):8872-8878. DOI: 10.1021/acsnano.9b02371. View

Le T, Winkler D . Discovery and Optimization of Materials Using Evolutionary Approaches. Chem Rev. 2016; 116(10):6107-32. DOI: 10.1021/acs.chemrev.5b00691. View

So S, Mun J, Rho J . Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles. ACS Appl Mater Interfaces. 2019; 11(27):24264-24268. DOI: 10.1021/acsami.9b05857. View

Chen Y, Zhu J, Xie Y, Feng N, Liu Q . Smart inverse design of graphene-based photonic metamaterials by an adaptive artificial neural network. Nanoscale. 2019; 11(19):9749-9755. DOI: 10.1039/c9nr01315f. View

Peurifoy J, Shen Y, Jing L, Yang Y, Cano-Renteria F, DeLacy B . Nanophotonic particle simulation and inverse design using artificial neural networks. Sci Adv. 2018; 4(6):eaar4206. PMC: 5983917. DOI: 10.1126/sciadv.aar4206. View

Khorasaninejad M, Chen W, Devlin R, Oh J, Zhu A, Capasso F . Metalenses at visible wavelengths: Diffraction-limited focusing and subwavelength resolution imaging. Science. 2016; 352(6290):1190-4. DOI: 10.1126/science.aaf6644. View

10.

Tang S, Cai T, Wang G, Liang J, Li X, Yu J . High-efficiency dual-modes vortex beam generator with polarization-dependent transmission and reflection properties. Sci Rep. 2018; 8(1):6422. PMC: 5913217. DOI: 10.1038/s41598-018-24929-4. View

11.

Byrnes S, Lenef A, Aieta F, Capasso F . Designing large, high-efficiency, high-numerical-aperture, transmissive meta-lenses for visible light. Opt Express. 2017; 24(5):5110-5124. DOI: 10.1364/OE.24.005110. View

12.

Winter R, Montanari F, Steffen A, Briem H, Noe F, Clevert D . Efficient multi-objective molecular optimization in a continuous latent space. Chem Sci. 2019; 10(34):8016-8024. PMC: 6836962. DOI: 10.1039/c9sc01928f. View

13.

Auguie B, Barnes W . Collective resonances in gold nanoparticle arrays. Phys Rev Lett. 2008; 101(14):143902. DOI: 10.1103/PhysRevLett.101.143902. View

14.

Ding F, Pors A, Bozhevolnyi S . Gradient metasurfaces: a review of fundamentals and applications. Rep Prog Phys. 2017; 81(2):026401. DOI: 10.1088/1361-6633/aa8732. View

15.

Zheng G, Muhlenbernd H, Kenney M, Li G, Zentgraf T, Zhang S . Metasurface holograms reaching 80% efficiency. Nat Nanotechnol. 2015; 10(4):308-12. DOI: 10.1038/nnano.2015.2. View

16.

Balin I, Garmider V, Long Y, Abdulhalim I . Training artificial neural network for optimization of nanostructured VO-based smart window performance. Opt Express. 2019; 27(16):A1030-A1040. DOI: 10.1364/OE.27.0A1030. View

17.

Zhou J, Huang B, Yan Z, Bunzli J . Emerging role of machine learning in light-matter interaction. Light Sci Appl. 2019; 8:84. PMC: 6804848. DOI: 10.1038/s41377-019-0192-4. View

18.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

19.

Hemmatyar O, Abdollahramezani S, Kiarashinejad Y, Zandehshahvar M, Adibi A . Full color generation with Fano-type resonant HfO nanopillars designed by a deep-learning approach. Nanoscale. 2019; 11(44):21266-21274. DOI: 10.1039/c9nr07408b. View

20.

Riley P . Three pitfalls to avoid in machine learning. Nature. 2019; 572(7767):27-29. DOI: 10.1038/d41586-019-02307-y. View