Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks

Abstract

A key challenge in metasurface design is the development of algorithms that can effectively and efficiently produce high performance devices. Design methods based on iterative optimization can push the performance limits of metasurfaces, but they require extensive computational resources that limit their implementation to small numbers of microscale devices. We show that generative neural networks can train from images of periodic, topology-optimized metagratings to produce high-efficiency, topologically complex devices operating over a broad range of deflection angles and wavelengths. Further iterative optimization of these designs yields devices with enhanced robustness and efficiencies, and these devices can be utilized as additional training data for network refinement. In this manner, generative networks can be trained, with a onetime computation cost, and used as a design tool to facilitate the production of near-optimal, topologically-complex device designs. We envision that such data-driven design methodologies can apply to other physical sciences domains that require the design of functional elements operating across a wide parameter space.

arXiv comment15 pages, 5 figures

References in corpus (11)

• Conditional Generative Adversarial Nets
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Dielectric Metasurfaces for Complete Control of Phase and Polarization with Subwavelength Spatial Resolution and High Transmission
• High-efficiency light-wave control with all-dielectric optical Huygens' metasurfaces
• Training deep neural networks for the inverse design of nanophotonic structures
• Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
• A Generative Model for Inverse Design of Metamaterials
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Topology Optimized Multi-layered Meta-optics
• RETICOLO software for grating analysis
• Freeform metagratings based on complex light scattering dynamics for extreme, high efficiency beam steering

Cited by in corpus (53)

• Deep neural networks for the evaluation and design of photonic devices
• Deep learning in nano-photonics: inverse design and beyond
• Tunable nanophotonics enabled by chalcogenide phase-change materials
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Data-Driven Design for Metamaterials and Multiscale Systems: A Review
• Meta-optics for spatial optical analog computing
• Simulator-based training of generative models for the inverse design of metasurfaces
• Solving integral equations in free-space with inverse-designed ultrathin optical metagratings
• Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms
• Active learning of deep surrogates for PDEs: Application to metasurface design
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Global Inverse Design Across Multiple Photonic Structure Classes Using Generative Deep Learning
• Machine learning-assisted design of material properties
• Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design
• Perfect diffraction metagratings supporting bound states in the continuum and exceptional points
• MetaNet: A new paradigm for data sharing in photonics research
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Neural reparameterization improves structural optimization
• A topological encoding method for data-driven photonics inverse design
• Rapid classification of quantum sources enabled by machine learning
• Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced transparency
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• Machine Learning Framework for Quantum Sampling of Highly-Constrained, Continuous Optimization Problems
• Deep neural networks for the prediction of the optical properties and the free-form inverse design of metamaterials
• Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
• Neural network design of multilayer metamaterial for temporal differentiation
• Physics-informed reinforcement learning for sample-efficient optimization of freeform nanophotonic devices
• Deep learning-based design of broadband GHz complex and random metasurfaces
• Multifunctional Metasurface Design with a Generative Adversarial Network
• Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
• Improving the beam quality factor ($M^2$) by phase-only reshaping of structured light
• Optimized geometries for cooperative photon storage in an impurity coupled to a two-dimensional atomic array
• A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks
• Integration of Programmable Diffraction with Digital Neural Networks
• Deep learning for nano-photonic materials -- The solution to everything!?
• Deep Inverse Design of Reconfigurable Metasurfaces for Future Communications
• Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• Generating extreme quantum scattering in graphene with machine learning
• Compounding meta-atoms into meta-molecules with hybrid artificial intelligence techniques
• Inverse design method for periodic and aperiodic metasurfaces based on the adjoint-method: metalens with random-like distributed nano-rods
• Inverse design of a 1D dielectric metasurface by topology optimization: fluctuations-trend analysis assisted by a diamond-square algorithm
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• Enhanced absorption per unit mass for infrared arrays using subwavelength metal-dielectric structures
• Hybrid design of spectral splitters and concentrators of light for solar cells using iterative search and neural networks
• Multiplexed Supercell Metasurface Design and Optimization with Tandem Residual Networks
• Neural-adjoint method for the inverse design of all-dielectric metasurfaces
• Design space reparameterization enforces hard geometric constraints in inverse-designed nanophotonic devices
• High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible
• A Framework for Discovering Optimal Solutions in Photonic Inverse Design
• Spectral splitting and concentration of broadband light using neural networks
• Ultra low loss broadband 1 $\times$ 2 optical power splitters with various splitting ratios