English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Metasurfaces have provided a novel and promising platform for the realizationof compact and large-scale optical devices. The conventional metasurface designapproach assumes periodic boundary conditions for each element, which isinaccurate in most cases since the near-field coupling effects between elementswill change when surrounded by non-identical structures. In this paper, wepropose a deep learning approach to predict the actual electromagnetic (EM)responses of each target meta-atom placed in a large array with near-fieldcoupling effects taken into account. The predicting neural network takes thephysical specifications of the target meta-atom and its neighbors as input, andcalculates its phase and amplitude in milliseconds. This approach can beapplied to explain metasurfaces' performance deterioration caused by mutualcoupling and further used to optimize their efficiencies once combined withoptimization algorithms. To demonstrate the efficacy of this methodology, weobtain large improvements in efficiency for a beam deflector and a metalensover the conventional design approach. Moreover, we show the correlationsbetween a metasurface's performance and its design errors caused by mutualcoupling are not bound to certain specifications (materials, shapes, etc.). Assuch, we envision that this approach can be readily applied to explore themutual coupling effects and improve the performance of various metasurfacedesigns.

Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces