Multiobjective and categorical global optimization of photonic structures based on ResNet generative neural networks

Jiang, Jiaqi; Fan, Jonathan A.

doi:10.1515/nanoph-2020-0407

Multiobjective and categorical global optimization of photonic structures based on ResNet generative neural networks

Journal Article · Tue Sep 22 00:00:00 EDT 2020 · Nanophotonics

DOI:https://doi.org/10.1515/nanoph-2020-0407· OSTI ID:1734938

Jiang, Jiaqi ^[1]; Fan, Jonathan A. ^[1]

Department of Electrical Engineering, Stanford University, 348 Via Pueblo, Stanford, CA94305, USA

Abstract

We show that deep generative neural networks, based on global optimization networks (GLOnets), can be configured to perform the multiobjective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof-of-concept demonstration, we adapt our method to design thin-film stacks consisting of multiple material types. Benchmarks with known globally optimized antireflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.

View Journal Article

Sponsoring Organization:: USDOE Advanced Research Projects Agency - Energy (ARPA-E)

Grant/Contract Number:: AR0001212

OSTI ID:: 1734938

Journal Information:: Nanophotonics, Journal Name: Nanophotonics Journal Issue: 1 Vol. 10; ISSN 2192-8606

Publisher:: Walter de Gruyter GmbHCopyright Statement

Country of Publication:: Germany

Language:: English

References (33)

Toward a High-Efficient Utilization of Solar Radiation by Quad-Band Solar Spectral Splitting Cao, Feng; Huang, Yi; Tang, Lu Advanced Materials, Vol. 28, Issue 48 https://doi.org/10.1002/adma.201603113	journal	October 2016
Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy Ma, Wei; Cheng, Feng; Xu, Yihao Advanced Materials, Vol. 31, Issue 35 https://doi.org/10.1002/adma.201901111	journal	July 2019
Freeform Metagratings Based on Complex Light Scattering Dynamics for Extreme, High Efficiency Beam Steering Yang, Jianji; Sell, David; Fan, Jonathan A. Annalen der Physik, Vol. 530, Issue 1 https://doi.org/10.1002/andp.201700302	journal	October 2017
1.5-octave chirped mirror for pulse compression down to sub-3 fs Pervak, V.; Tikhonravov, A. V.; Trubetskov, M. K. Applied Physics B, Vol. 87, Issue 1 https://doi.org/10.1007/s00340-006-2467-8	journal	October 2006
Global optimal design of optical multilayer thin-film filters using particle swarm optimization Rabady, Rabi I.; Ababneh, Almahdi Optik, Vol. 125, Issue 1 https://doi.org/10.1016/j.ijleo.2013.07.028	journal	January 2014
Large-Angle, Multifunctional Metagratings Based on Freeform Multimode Geometries Sell, David; Yang, Jianji; Doshay, Sage Nano Letters, Vol. 17, Issue 6 https://doi.org/10.1021/acs.nanolett.7b01082	journal	May 2017
Generative Model for the Inverse Design of Metasurfaces Liu, Zhaocheng; Zhu, Dayu; Rodrigues, Sean P. Nano Letters, Vol. 18, Issue 10 https://doi.org/10.1021/acs.nanolett.8b03171	journal	September 2018
Global Optimization of Dielectric Metasurfaces Using a Physics-Driven Neural Network Jiang, Jiaqi; Fan, Jonathan A. Nano Letters, Vol. 19, Issue 8 https://doi.org/10.1021/acs.nanolett.9b01857	journal	July 2019
Free-Form Diffractive Metagrating Design Based on Generative Adversarial Networks Jiang, Jiaqi; Sell, David; Hoyer, Stephan ACS Nano, Vol. 13, Issue 8 https://doi.org/10.1021/acsnano.9b02371	journal	July 2019
Inverse Design of Photonic Crystals through Automatic Differentiation Minkov, Momchil; Williamson, Ian A. D.; Andreani, Lucio C. ACS Photonics, Vol. 7, Issue 7 https://doi.org/10.1021/acsphotonics.0c00327	journal	June 2020
Robust Freeform Metasurface Design Based on Progressively Growing Generative Networks Wen, Fufang; Jiang, Jiaqi; Fan, Jonathan A. ACS Photonics, Vol. 7, Issue 8 https://doi.org/10.1021/acsphotonics.0c00539	journal	June 2020
A Comprehensive Photonic Approach for Solar Cell Cooling Li, Wei; Shi, Yu; Chen, Kaifeng ACS Photonics, Vol. 4, Issue 4 https://doi.org/10.1021/acsphotonics.7b00089	journal	March 2017
Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures Liu, Dianjing; Tan, Yixuan; Khoram, Erfan ACS Photonics, Vol. 5, Issue 4 https://doi.org/10.1021/acsphotonics.7b01377	journal	January 2018
Adjoint Method and Inverse Design for Nonlinear Nanophotonic Devices Hughes, Tyler W.; Minkov, Momchil; Williamson, Ian A. D. ACS Photonics, Vol. 5, Issue 12 https://doi.org/10.1021/acsphotonics.8b01522	journal	November 2018
Forward-Mode Differentiation of Maxwell’s Equations Hughes, Tyler W.; Williamson, Ian A. D.; Minkov, Momchil ACS Photonics, Vol. 6, Issue 11 https://doi.org/10.1021/acsphotonics.9b01238	journal	September 2019
Passive radiative cooling below ambient air temperature under direct sunlight Raman, Aaswath P.; Anoma, Marc Abou; Zhu, Linxiao Nature, Vol. 515, Issue 7528, p. 540-544 https://doi.org/10.1038/nature13883	journal	November 2014
A nanophotonic solar thermophotovoltaic device Lenert, Andrej; Bierman, David M.; Nam, Youngsuk Nature Nanotechnology, Vol. 9, Issue 2, p. 126-130 https://doi.org/10.1038/nnano.2013.286	journal	January 2014
Tailoring high-temperature radiation and the resurrection of the incandescent source Ilic, Ognjen; Bermel, Peter; Chen, Gang Nature Nanotechnology, Vol. 11, Issue 4 https://doi.org/10.1038/nnano.2015.309	journal	January 2016
Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer Piggott, Alexander Y.; Lu, Jesse; Lagoudakis, Konstantinos G. Nature Photonics, Vol. 9, Issue 6, p. 374-377 https://doi.org/10.1038/nphoton.2015.69	journal	May 2015
Inverse design in nanophotonics Molesky, Sean; Lin, Zin; Piggott, Alexander Y. Nature Photonics, Vol. 12, Issue 11 https://doi.org/10.1038/s41566-018-0246-9	journal	October 2018
Guaranteed global optimization of thin-film optical systems Azunre, Paul; Jean, Joel; Rotschild, Carmel New Journal of Physics, Vol. 21, Issue 7 https://doi.org/10.1088/1367-2630/ab2e19	journal	July 2019
Wavelength demultiplexer using the spatial dispersion of multilayer thin-film structures Gerken, M.; Miller, D. A. B. IEEE Photonics Technology Letters, Vol. 15, Issue 8 https://doi.org/10.1109/LPT.2003.815318	journal	August 2003
Nanophotonic particle simulation and inverse design using artificial neural networks Peurifoy, John; Shen, Yichen; Jing, Li Science Advances, Vol. 4, Issue 6 https://doi.org/10.1126/sciadv.aar4206	journal	June 2018
Optical Broadband Angular Selectivity Shen, Y.; Ye, D.; Celanovic, I. Science, Vol. 343, Issue 6178, p. 1499-1501 https://doi.org/10.1126/science.1249799	journal	March 2014
Application of the needle optimization technique to the design of optical coatings Tikhonravov, Alexander V.; Trubetskov, Michael K.; DeBell, Gary W. Applied Optics, Vol. 35, Issue 28 https://doi.org/10.1364/AO.35.005493	journal	January 1996
Optical coating design approaches based on the needle optimization technique Tikhonravov, A. V.; Trubetskov, M. K.; DeBell, G. W. Applied Optics, Vol. 46, Issue 5 https://doi.org/10.1364/AO.46.000704	journal	January 2007
Objective-first design of high-efficiency, small-footprint couplers between arbitrary nanophotonic waveguide modes Lu, Jesse; Vučković, Jelena Optics Express, Vol. 20, Issue 7 https://doi.org/10.1364/OE.20.007221	journal	January 2012
Thin-film multilayer design optimization using a Monte Carlo approach Wild, W. J.; Buhay, H. Optics Letters, Vol. 11, Issue 11 https://doi.org/10.1364/OL.11.000745	journal	January 1986
Review of numerical optimization techniques for meta-device design [Invited] Campbell, Sawyer D.; Sell, David; Jenkins, Ronald P. Optical Materials Express, Vol. 9, Issue 4 https://doi.org/10.1364/OME.9.001842	journal	January 2019
Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale Yao, Kan; Unni, Rohit; Zheng, Yuebing Nanophotonics, Vol. 8, Issue 3 https://doi.org/10.1515/nanoph-2018-0183	journal	January 2019
Simulator-based training of generative neural networks for the inverse design of metasurfaces Jiang, Jiaqi; Fan, Jonathan A. Nanophotonics, Vol. 9, Issue 5 https://doi.org/10.1515/nanoph-2019-0330	journal	November 2019
Deep learning enabled inverse design in nanophotonics So, Sunae; Badloe, Trevon; Noh, Jaebum Nanophotonics, Vol. 9, Issue 5 https://doi.org/10.1515/nanoph-2019-0474	journal	February 2020
Freeform metasurface design based on topology optimization Fan, Jonathan A. MRS Bulletin, Vol. 45, Issue 3 https://doi.org/10.1557/mrs.2020.62	journal	March 2020

Similar Records

Heuristic methods and performance bounds for photonic design

Journal Article · Thu Jan 14 19:00:00 EST 2021 · Optics Express · OSTI ID:1760056

Application of neural networks in computing multiobjective stochastic programming

Conference · Fri Dec 30 23:00:00 EST 1994 · OSTI ID:35994

Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II

Conference · Tue Aug 01 00:00:00 EDT 2023 · OSTI ID:1996670

Multiobjective and categorical global optimization of photonic structures based on ResNet generative neural networks

Citation Formats

References (33)

Similar Records

Related Subjects