A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks

Abstract

Metasurfaces have shown promising potentials in shaping optical wavefronts while remaining compact compared to bulky geometric optics devices. Design of meta-atoms, the fundamental building blocks of metasurfaces, relies on trial-and-error method to achieve target electromagnetic responses. This process includes the characterization of an enormous amount of different meta-atom designs with different physical and geometric parameters, which normally demands huge computational resources. In this paper, a deep learning-based metasurface/meta-atom modeling approach is introduced to significantly reduce the characterization time while maintaining accuracy. Based on a convolutional neural network (CNN) structure, the proposed deep learning network is able to model meta-atoms with free-form 2D patterns and different lattice sizes, material refractive indexes and thicknesses. Moreover, the presented approach features the capability to predict meta-atoms' wide spectrum responses in the timescale of milliseconds, which makes it attractive for applications such as fast meta-atom/metasurface on-demand designs and optimizations.

References in corpus (5)

• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Generalized effective-medium theory for metamaterials
• A Novel Modeling Approach for All-Dielectric Metasurfaces Using Deep Neural Networks
• A Hybrid Strategy for the Discovery and Design of Photonic Nanostructures
• Compounding meta-atoms into meta-molecules with hybrid artificial intelligence techniques