Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces

  title={Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces},
  author={Sensong An and Bowen Zheng and Mikhail Y. Shalaginov and Hong Tang and Hang Li and Li Zhou and Yunxi Dong and Mohammad Haerinia and Anuradha Murthy Agarwal and Clara Rivero‐Baleine and Myungkoo Kang and Kathleen A. Richardson and Tian Gu and Juejun Hu and Clayton Fowler and Hualiang Zhang},
Metasurfaces have provided a novel and promising platform for the realization of compact and large-scale optical devices. The conventional metasurface design approach assumes periodic boundary conditions for each element, which is inaccurate in most cases since the nearfield coupling effects between elements will change when surrounded by non-identical structures. In this paper, we propose a deep learning approach to predict the actual electromagnetic (EM) responses of each target meta-atom… Expand
1 Citations

Figures from this paper

Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
Optical interactions have an important impact on the optical response of nanostructures in complex environments. Accounting for interactions in large ensembles of structures requires computationallyExpand


Deep learning modeling approach for metasurfaces with high degrees of freedom.
A deep learning-based metasurface/meta-atom modeling approach is introduced to significantly reduce the characterization time while maintaining accuracy, and features the capability of predicting a meta-atom's wide spectrum response in the timescale of milliseconds. Expand
Generative Model for the Inverse Design of Metasurfaces
The advent of metasurfaces in recent years has ushered in a revolutionary means to manipulate the behavior of light on the nanoscale. The design of such structures, to date, has relied on theExpand
A Generative Model for Inverse Design of Metamaterials
This work identifies a solution to circumvent this conventional design procedure by means of a deep learning architecture to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner. Expand
Local phase method for designing and optimizing metasurface devices.
Quantifying the phase error of each element of the metasurfaces with the proposed local phase method paves the way to the design of highly efficient metasURface devices including, but not limited to, deflectors, high numerical aperture metasulface concentrators, lenses, cloaks, and modulators. Expand
A Hybrid Strategy for the Discovery and Design of Photonic Structures
This work represents an efficient, on-demand, and automated approach for the inverse design of photonic structures with subwavelength features and requires no prior knowledge of the geometry of thePhotonic structures, and allows joint optimization of the dimensional parameters. Expand
Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks.
It is shown 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. Expand
Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials.
A deep-learning-based model is reported, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths. Expand
Periodic Dielectric Metasurfaces with High‐Efficiency, Multiwavelength Functionalities
Metasurfaces are thin-film optical devices for tailoring the phase fronts of light. The extension of metasurfaces to multiple wavelengths has remained a major challenge, and existing designExpand
Inverse design of large-area metasurfaces.
A "locally periodic" approximation is employed in which the scattering problem is approximated by a composition of periodic scattering problems from each unit cell of the surface, and validated against brute-force Maxwell solutions. Expand
Reconfigurable all-dielectric metalens with diffraction-limited performance
This paper introduces an active metasurface platform combining phase tuning in the full 2π range and diffraction-limited performance using an all-dielectric, low-loss architecture based on optical phase change materials (O-PCMs). Expand