Deep-Learning-Empowered Holographic Metasurface with Simultaneously Customized Phase and Amplitude

Abstract

Metasurfaces with simultaneously and independently controllable amplitude and phase have provided a higher degree of freedom in manipulating electromagnetic (EM) waves. Compared with phase- or amplitude-only modulation, the capability of simultaneously controlling the phase and amplitude of EM waves can enable holography with a higher resolution. However, this drastically increases the design complexity of holographic metasurfaces, and the design process is usually quite time-consuming. In this paper, we propose an inverse design of meta-atoms that can simultaneously and independently tailor the phase and amplitude of transmitted waves using customized deep ResNet while eliminating the coupling of parameters. To demonstrate the design method, two holographic metasurfaces were designed using the trained network without the need for parameter sweeping, which will significantly enhance design efficiency. Prototypes were fabricated and measured. Both the simulated and measured results show that high-resolution holography is obtained, which sufficiently verifies the reliability of the design method. Our work paves the way for the intelligent design of metasurfaces and can also be applied to the design of other artificial materials or surfaces.

Carbon dots with tissue engineering and regenerative medicine applications

“…It was revealed that TCDs-CaO 2 -ZE had excellent biocompatibility and anti-inflammatory effects as well as enhanced wound healing properties in diabetic rats without any cytotoxicity. 71 In another study, Qu et al 72 designed sprayable positively charged CDs for promoting infected wound healing. These CDs were synthesized from p -phenylenediamine and polyethyleneimine by a facile one-pot solvothermal method.…”

“…Its sprayable forms were also used to treat a skin infection in mouse model, and the results were promising in promoting would healing without causing any noticeable side effects. 72…”

Uncertainty Qualification for Metasurface Design with Amendatory Bayesian Network

“…[23] Due to its initial data-driven methodology, deep learning has become a powerful driving force in the context of metasurface design from forward design to inverse design. [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42] Taking the inverse design of the metasurface for instance, the deep neural networks can unfold abstract information automatically from a considerably large amount of data pairs of geometrical structures and corresponding spectral response. [35] Compared with conventional physical-and rule-based methods, deep-learning-assisted metasurface design gets rid of repeated manual labor and timeconsuming simulations and reduces the reliance on specialist experience.…”

Carbon dots with high quantum yields used for Fe3+ detection, information encryption and anti-counterfeiting

“…Carbon dots are a new member of the carbon nanomaterial family, first reported by Xu et al 25 in 2004 and have soon aroused the interest of researchers in various fields. [26][27][28] Compared to traditional semiconductor quantum dots, CDs have superior optical properties, 29,30 good water solubility, [31][32][33] easyto-modify surface [34][35][36] and good dispersion. [37][38][39] Due to these advantages, CDs are increasingly being utilized as fluorescent probes.…”