A Generative Model for Inverse Design of Metamaterials

Abstract

The advent of two-dimensional metamaterials in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale. The effective parameters of these architected materials render unprecedented control over the optical properties of light, thereby eliciting previously unattainable applications in flat lenses, holographic imaging, and emission control among others. The design of such structures, to date, has relied on the expertise of an optical scientist to guide a progression of electromagnetic simulations that iteratively solve Maxwell's equations until a locally optimized solution can be attained. In this work, we identify a solution to circumvent this intuition-guided design by means of a deep learning architecture. When fed an input set of optical spectra, the constructed generative network assimilates a candidate pattern from a user-defined dataset of geometric structures in order to match the input spectra. The generated metamaterial patterns demonstrate high fidelity, yielding equivalent optical spectra at an average accuracy of about 0.9. This approach reveals an opportunity to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner.

15 pages, 4 figures

References in corpus (13)

• A Perfect Metamaterial Absorber
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Dielectric Metasurfaces for Complete Control of Phase and Polarization with Subwavelength Spatial Resolution and High Transmission
• Learning to Plan Chemical Syntheses
• Improved Training of Wasserstein GANs
• Machine learning phases of matter
• Training deep neural networks for the inverse design of nanophotonic structures
• Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
• Active learning machine learns to create new quantum experiments
• Nanophotonic Computational Design
• Topology Optimized Multi-layered Meta-optics
• Evolutionary Multi-Objective Optimisation of Colour Pixels based on Dielectric Nano-Antennas
• Inverse designed photonic fibers and metasurfaces for nonlinear frequency conversion

Cited by in corpus (110)

• 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
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Intelligent Nanophotonics: Merging Photonics and Artificial Intelligence at the Nanoscale
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Data-Driven Design for Metamaterials and Multiscale Systems: A Review
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
• A Generative Machine Learning-Based Approach for Inverse Design of Multilayer Metasurfaces
• Meta-optics for spatial optical analog computing
• Simulator-based training of generative models for the inverse design of metasurfaces
• Dynamic hybrid metasurfaces
• Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition
• Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices
• Unsupervised Manifold Clustering of Topological Phononics
• Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms
• Knowledge Discovery In Nanophotonics Using Geometric Deep Learning
• Plasmonic colours predicted by deep learning
• IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
• Overlapping domains for topology optimization of large-area metasurfaces
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Designing Silicon Photonic Devices using Artificial Neural Networks
• Global Inverse Design Across Multiple Photonic Structure Classes Using Generative Deep Learning
• Machine learning-assisted design of material properties
• Deterministic and probabilistic deep learning models for inverse design of broadband acoustic cloak
• Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design
• Iterative optimization of photonic crystal nanocavity designs by using deep neural networks
• 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
• Mapping the Design Space of Photonic Topological States via Deep Learning
• A topological encoding method for data-driven photonics inverse design
• Error Analysis of Programmable Metasurfaces for Beam Steering
• Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced transparency
• Independent Control of Multiple Channels in Metasurface Devices
• A Comprehensive and Versatile Multimodal Deep Learning Approach for Predicting Diverse Properties of Advanced Materials
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
• A Combined Machine-Learning / Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces
• Fast Design of Plasmonic Metasurfaces Enabled by Deep Learning
• Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning
• Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
• Deep neural networks for the prediction of the optical properties and the free-form inverse design of metamaterials
• Fast simulation of light scattering and harmonic generation in axially symmetric structures in COMSOL
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• Machine Learning Assisted Inverse Design of Microresonators
• Neural network design of multilayer metamaterial for temporal differentiation
• Efficient inverse design and spectrum prediction for nanophotonic devices based on deep recurrent neural networks
• Deep learning-based design of broadband GHz complex and random metasurfaces
• Parameterized Reinforcement Learning for Optical System Optimization
• Engineering photonic environments for two-dimensional materials
• Deep-Learning-Enabled Inverse Engineering of Multi-Wavelength Invisibility-to-Superscattering Switching with Phase-Change Materials
• Machine learning identifies scale-free properties in disordered materials
• Multifunctional Metasurface Design with a Generative Adversarial Network
• Over 30,000-fold field enhancement of terahertz nanoresonators enabled by rapid inverse design
• Machine prediction of topological transitions in photonic crystals
• Circularly Polarized Fabry-Perot Cavity Sensing Antenna Design using Generative Model
• GRIDS-Net: Inverse shape design and identification of scatterers via geometric regularization and physics-embedded deep learning
• Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres
• Benchmarking deep inverse models over time, and the neural-adjoint method
• Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
• Predicting nonlinear optical scattering with physics-driven neural networks
• A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• PyMoosh : a comprehensive numerical toolkit for computing the optical properties of multilayered structures
• Integration of Programmable Diffraction with Digital Neural Networks
• Deep Neural Operator Enabled Concurrent Multitask Design for Multifunctional Metamaterials under Heterogeneous Fields
• Multiple scattering simulation via physics-informed neural networks
• A Novel Modeling Approach for All-Dielectric Metasurfaces Using Deep Neural Networks
• Deep learning for nano-photonic materials -- The solution to everything!?
• Deep Inverse Design of Reconfigurable Metasurfaces for Future Communications
• Photonics in Flatland: Challenges and Opportunities for Nanophotonics with 2D Semiconductors
• Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces
• Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• Generating extreme quantum scattering in graphene with machine learning
• Machine Learning-Based Optimization of Chiral Photonic Nanostructures: Evolution- and Neural Network-Based Design
• Broadband Unidirectional Visible Imaging Using Wafer-Scale Nano-Fabrication of Multi-Layer Diffractive Optical Processors
• Investigation on optimal microstructure of dual-phase steel with high strength and ductility by machine learning
• Compounding meta-atoms into meta-molecules with hybrid artificial intelligence techniques
• Predicting VCSEL Emission Properties Using Transformer Neural Networks
• Broadband Polarization-Independent Achromatic Metalenses with Unintuitively-Designed Random-Shaped Meta-Atoms
• Spectral domain inverse design for accelerating nanocomposite metamaterials discovery
• Simultaneous inverse design of materials and parameters of core-shell nanoparticle via deep-learning: Demonstration of dipole resonance engineering
• Analysis and design of transition radiation in layered uniaxial crystals using Tandem neural networks
• Enhanced absorption per unit mass for infrared arrays using subwavelength metal-dielectric structures
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• Deep-learning design of graphene metasurfaces for quantum control and Dirac electron holography
• Multiplexed Supercell Metasurface Design and Optimization with Tandem Residual Networks
• Neural-adjoint method for the inverse design of all-dielectric metasurfaces
• A universal deep learning strategy for designing high-quality-factor photonic resonances
• Probabilistic representation and inverse design of metamaterials based on a deep generative model with semi-supervised learning strategy
• Estimation of Electrical Characteristics of Complex Walls Using Deep Neural Networks
• AI based design of 2D material integrated optical polarizers
• A General Expression for Homogeneous Metasurface Scattering
• Poles of the Scattering Matrix: An Inverse Method for Designing Photonic Resonators
• Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm
• Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter
• High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible
• Interpretable inverse design of particle spectral emissivity using machine learning
• A Framework for Discovering Optimal Solutions in Photonic Inverse Design
• Ultra low loss broadband 1 $\times$ 2 optical power splitters with various splitting ratios
• Broadband vectorial ultra-flat optics with experimental efficiency up to 99% in the visible via universal approximators
• A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes
• Spectra2pix: Generating Nanostructure Images from Spectra
• Wavelength Controllable Forward Prediction and Inverse Design of Nanophotonic Devices Using Deep Learning
• Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN
• A Quantum-Inspired Probabilistic Model for the Inverse Design of Meta-Structures
• Emissivity Prediction of Functionalized Surfaces Using Artificial Intelligence