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

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.

[1]  Kyu-Tae Lee,et al.  A Generative Model for Inverse Design of Metamaterials , 2018, Nano letters.

[2]  Shanhui Fan,et al.  Adjoint Method and Inverse Design for Nonlinear Nanophotonic Devices , 2018, ACS Photonics.

[3]  Alexander Y. Piggott,et al.  Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer , 2015, Nature Photonics.

[4]  Jonathan A. Fan,et al.  Global optimization of dielectric metasurfaces using a physics-driven neural network , 2019, Nano letters.

[5]  Ian A. D. Williamson,et al.  Inverse design of photonic crystals through automatic differentiation , 2020, ArXiv.

[6]  Christine Silberhorn,et al.  Metasurface interferometry toward quantum sensors , 2019, Light, science & applications.

[7]  Jelena Vucković,et al.  Inverse design in nanophotonics , 2018, Nature Photonics.

[8]  A. Tikhonravov,et al.  Optical coating design approaches based on the needle optimization technique. , 2007, Applied optics.

[9]  Steven G. Johnson,et al.  Optical Broadband Angular Selectivity , 2014, Science.

[10]  Jiaqi Jiang,et al.  Robust Freeform Metasurface Design Based on Progressively Growing Generative Networks , 2020, ACS Photonics.

[11]  Steven G. Johnson,et al.  Guaranteed global optimization of thin-film optical systems , 2019, New Journal of Physics.

[12]  W. Marsden.  I and J , 2012 .

[13]  Zongfu Yu,et al.  Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures , 2017, 2019 Conference on Lasers and Electro-Optics (CLEO).

[14]  W J Wild,et al.  Thin-film multilayer design optimization using a Monte Carlo approach. , 1986, Optics letters.

[15]  Shanhui Fan,et al.  A Comprehensive Photonic Approach for Solar Cell Cooling , 2017 .

[16]  Jonathan A. Fan,et al.  Freeform metasurface design based on topology optimization , 2020, MRS Bulletin.

[17]  Feng Cheng,et al.  Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy , 2019, Advanced materials.

[18]  Marc Abou Anoma,et al.  Passive radiative cooling below ambient air temperature under direct sunlight , 2014, Nature.

[19]  David Sell,et al.  Large-Angle, Multifunctional Metagratings Based on Freeform Multimode Geometries. , 2017, Nano letters.

[20]  Jonathan A. Fan,et al.  Review of numerical optimization techniques for meta-device design [Invited] , 2019, Optical Materials Express.

[21]  Ian A. D. Williamson,et al.  Forward-Mode Differentiation of Maxwell's Equations , 2019, ACS Photonics.

[22]  Rabi Rabady,et al.  Global optimal design of optical multilayer thin-film filters using particle swarm optimization , 2014 .

[23]  David Sell,et al.  Freeform Metagratings Based on Complex Light Scattering Dynamics for Extreme, High Efficiency Beam Steering , 2017, 1709.05019.

[24]  Jesse Lu,et al.  Objective-first design of high-efficiency, small-footprint couplers between arbitrary nanophotonic waveguide modes. , 2012, Optics express.

[25]  Jason Hickey,et al.  Data-driven metasurface discovery , 2018, ACS nano.

[26]  M. Gerken,et al.  Wavelength demultiplexer using the spatial dispersion of multilayer thin-film structures , 2003, IEEE Photonics Technology Letters.

[27]  Yuebing Zheng,et al.  Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale , 2018, Nanophotonics.

[28]  Trevon Badloe,et al.  Deep learning enabled inverse design in nanophotonics , 2020, Nanophotonics.

[29]  S. Boriskina,et al.  Toward a High‐Efficient Utilization of Solar Radiation by Quad‐Band Solar Spectral Splitting , 2016, Advanced materials.

[30]  A. Tikhonravov,et al.  Application of the needle optimization technique to the design of optical coatings. , 1996, Applied optics.

[31]  Yi Yang,et al.  Nanophotonic particle simulation and inverse design using artificial neural networks , 2018, Science Advances.

[32]  Alexander V. Tikhonravov,et al.  1.5-octave chirped mirror for pulse compression down to sub-3 fs , 2007 .

[33]  Jonathan A. Fan,et al.  Simulator-based training of generative neural networks for the inverse design of metasurfaces , 2019, Nanophotonics.

[34]  M. Soljačić,et al.  Tailoring high-temperature radiation and the resurrection of the incandescent source. , 2016, Nature nanotechnology.

[35]  David M. Bierman,et al.  A nanophotonic solar thermophotovoltaic device. , 2014, Nature nanotechnology.