A Novel Modeling Approach for All-Dielectric Metasurfaces Using Deep Neural Networks

Abstract

Metasurfaces have become a promising means for manipulating optical wavefronts in flat and high-performance optical devices. Conventional metasurface device design relies on trial-and-error methods to obtain target electromagnetic (EM) response, an approach that demands significant efforts to investigate the enormous number of possible meta-atom structures. In this paper, a deep neural network approach is introduced that significantly improves on both speed and accuracy compared to techniques currently used to assemble metasurface-based devices. Our neural network approach overcomes three key challenges that have limited previous neural-network-based design schemes: input/output vector dimensional mismatch, accurate EM-wave phase prediction, as well as adaptation to 3-D dielectric structures, and can be generically applied to a wide variety of metasurface device designs across the entire electromagnetic spectrum. Using this new methodology, examples of neural networks capable of producing on-demand designs for meta-atoms, metasurface filters, and phase-change reconfigurable metasurfaces are demonstrated.

arXiv comment18 pages, 8 figures

References in corpus (9)

• Dielectric Metasurfaces for Complete Control of Phase and Polarization with Subwavelength Spatial Resolution and High Transmission
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Deep learning for universal linear embeddings of nonlinear dynamics
• High-efficiency light-wave control with all-dielectric optical Huygens' metasurfaces
• Training deep neural networks for the inverse design of nanophotonic structures
• A Generative Model for Inverse Design of Metamaterials
• Achromatic Metalens in the Visible and Metalens with Reverse Chromatic Dispersion
• Decoupling optical function and geometrical form using conformal flexible dielectric metasurfaces
• Generalized effective-medium theory for metamaterials

Cited by in corpus (4)

• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Multifunctional Metasurface Design with a Generative Adversarial Network
• A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks
• Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm