Litcius/Paper detail

Deep learning for electromagnetically induced transparency (EIT) metasurface optimization design

Lei Zhu, Cong Zhang, Jing Guo, Dong Liang, Jinyue Gong

2022Journal of Physics D Applied Physics23 citationsDOI

Abstract

Abstract In order to accelerate the design process of electromagnetically induced transparency (EIT) metasurface, a deep learning-based EIT metasurface design method is proposed, where the spectral profile of EIT metasurface can be predicted by the forward prediction process, and the EIT metasurface geometry parameters based on the target spectral profile can be obtained by the inverse design process. In the inverse design process, a cascaded convolutional neural network (CNN) consisting of one-dimensional convolutional layer, a batch normalization layer, a pooling layer and an exponential linear unit (ELU) activation function is employed. Each CNN is designed to achieve feature extraction for spectra. The inverse network achieves low mean square errors (MSE), with MSE of 0.011 on the validation sets. After training, the model can more accurately predict the parameters with error of 0.3 μ m. This method is more efficient and saves computing resources, allowing designers to focus on the target spectra. More importantly, it can be extended to the design of arbitrary metasurface.

Topics & Concepts

Normalization (sociology)Electromagnetically induced transparencyInverseComputer scienceConvolutional neural networkMean squared errorAlgorithmInversion (geology)Inverse problemElectronic engineeringOpticsArtificial intelligencePhysicsMathematicsEngineeringMathematical analysisBiologyAnthropologySociologyStatisticsStructural basinPaleontologyGeometryMetamaterials and Metasurfaces ApplicationsAdvanced Antenna and Metasurface TechnologiesMillimeter-Wave Propagation and Modeling
Deep learning for electromagnetically induced transparency (EIT) metasurface optimization design | Litcius