Topological encoding method for data-driven photonics inverse design.

Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approaches for accurate and global optimization.

[1]  Yuri S. Kivshar,et al.  Quantum metasurface for multiphoton interference and state reconstruction , 2018, Science.

[2]  T. Gaylord,et al.  Formulation for stable and efficient implementation of the rigorous coupled-wave analysis of binary gratings , 1995 .

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

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

[5]  Peter R Wiecha,et al.  Evolutionary Multi-Objective Optimisation of Colour Pixels based on Dielectric Nano-Antennas , 2016, 1609.06709.

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  C. T. Chan,et al.  Machine prediction of topological transitions in photonic crystals. , 2019 .

[8]  W. Cai,et al.  A Generative Model for Inverse Design of Metamaterials , 2018, Nano letters.

[9]  Erez Hasman,et al.  Dielectric gradient metasurface optical elements , 2014, Science.

[10]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[11]  Trevon Badloe,et al.  Optimisation of colour generation from dielectric nanostructures using reinforcement learning. , 2019, Optics express.

[12]  Wei Chen,et al.  Highly Efficient Light-Trapping Structure Design Inspired By Natural Evolution , 2013, Scientific Reports.

[13]  Toshiaki Koike-Akino,et al.  Deep Neural Network Inverse Design of Integrated Photonic Power Splitters , 2019, Scientific Reports.

[14]  O. Sigmund,et al.  Topology optimization for nano‐photonics , 2011 .

[15]  Zhaocheng Liu,et al.  Metasurfaces for near-eye augmented reality , 2019, ACS Photonics.

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

[17]  F Roddier,et al.  Wavefront reconstruction using iterative Fourier transforms. , 1991, Applied optics.

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  J. Mockus.  Bayesian Approach to Global Optimization: Theory and Applications , 1989 .

[20]  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.

[21]  Gui-Lan Yu,et al.  Neural networks for inverse design of phononic crystals , 2019, AIP Advances.

[22]  Xu Han,et al.  Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks , 2018, Photonics Research.

[23]  Ravi S. Hegde,et al.  Photonics Inverse Design: Pairing Deep Neural Networks With Evolutionary Algorithms , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[24]  Inki Kim,et al.  Biomimetic Ultra-Broadband Perfect Absorbers Optimised with Reinforcement Learning , 2020, Physical chemistry chemical physics : PCCP.

[25]  N. Yu,et al.  Light Propagation with Phase Discontinuities: Generalized Laws of Reflection and Refraction , 2011, Science.

[26]  Zhaocheng Liu,et al.  Compounding Meta‐Atoms into Metamolecules with Hybrid Artificial Intelligence Techniques , 2019, Advanced materials.

[27]  Zhaocheng Liu,et al.  A Hybrid Strategy for the Discovery and Design of Photonic Structures , 2019, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[28]  Yongmin Liu,et al.  Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials. , 2018, ACS nano.

[29]  Byoungho Lee,et al.  Metasurface eyepiece for augmented reality , 2018, Nature Communications.

[30]  Vladimir M. Shalaev,et al.  Machine-learning-assisted metasurface design for high-efficiency thermal emitter optimization , 2019, 1910.12741.

[31]  T. Asano,et al.  Optimization of photonic crystal nanocavities based on deep learning. , 2018, Optics express.

[32]  O. Bryngdahl,et al.  Iterative Fourier-transform algorithm applied to computer holography , 1988 .

[33]  W. T. Chen,et al.  Metalenses at visible wavelengths: Diffraction-limited focusing and subwavelength resolution imaging , 2016, Science.

[34]  Michael Mrejen,et al.  Plasmonic nanostructure design and characterization via Deep Learning , 2018, Light: Science & Applications.

[35]  Xiangang Luo,et al.  Subwavelength Artificial Structures: Opening a New Era for Engineering Optics , 2018, Advanced materials.

[36]  Panos M. Pardalos,et al.  Multilevel Optimization: Algorithms and Applications , 2012 .

[37]  Junsuk Rho,et al.  Designing nanophotonic structures using conditional deep convolutional generative adversarial networks , 2019, Nanophotonics.

[38]  Peter R. Wiecha,et al.  Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures. , 2019, Nano letters.