Simulator-based training of generative models for the inverse design of metasurfaces

Abstract

Metasurfaces are subwavelength-structured artificial media that can shape and localize electromagnetic waves in unique ways. The inverse design of these devices is a non-convex optimization problem in a high dimensional space, making global optimization a major challenge. We present a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network. The loss function used for backpropagation depends on the generated pattern layouts, their efficiencies, and efficiency gradients, which are calculated by the adjoint variables method using forward and adjoint electromagnetic simulations. We observe that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization. Upon training completion, the best generated devices have efficiencies comparable to or exceeding the best devices designed using standard topology optimization. Our proposed global optimization algorithm can generally apply to other gradient-based optimization problems in optics, mechanics and electronics.

13 pages, 7 figures

References in corpus (7)

• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• A Generative Model for Inverse Design of Metamaterials
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Adjoint method and inverse design for nonlinear nanophotonic devices
• RETICOLO software for grating analysis
• Freeform metagratings based on complex light scattering dynamics for extreme, high efficiency beam steering

Cited by in corpus (22)

• Deep neural networks for the evaluation and design of photonic devices
• Data-Driven Design for Metamaterials and Multiscale Systems: A Review
• A Generative Machine Learning-Based Approach for Inverse Design of Multilayer Metasurfaces
• Enhanced Light-Matter Interactions in Dielectric Nanostructures via Machine Learning Approach
• Active learning of deep surrogates for PDEs: Application to metasurface design
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Towards 3D-Printed Inverse-Designed Metaoptics
• A neural operator-based surrogate solver for free-form electromagnetic inverse design
• A Combined Machine-Learning / Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces
• Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning
• Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning
• Global $\mathbb{T}$ operator bounds on electromagnetic scattering: Upper bounds on far-field cross sections
• Physics-informed reinforcement learning for sample-efficient optimization of freeform nanophotonic devices
• Deep-Learning-Enabled Inverse Engineering of Multi-Wavelength Invisibility-to-Superscattering Switching with Phase-Change Materials
• A directional Gaussian smoothing optimization method for computational inverse design in nanophotonics
• A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Broadband Polarization-Independent Achromatic Metalenses with Unintuitively-Designed Random-Shaped Meta-Atoms
• Deep learning for the modeling and inverse design of radiative heat transfer
• Efficient perturbative framework for coupling of radiative and guided modes in nearly periodic surfaces
• Design space reparameterization enforces hard geometric constraints in inverse-designed nanophotonic devices