Search

Metamaterial absorbers have become a popular research direction due to their broad application prospects, such as in radar, infrared imaging, and solar cell fields. Usually, nanostructured metamaterials are associated with a large number of geometric parameters, and traditional simulation designs are time consuming. In this paper, we propose a framework for designing plasma metamaterial absorbers in both a forward prediction and inverse design composed of a primary prediction network (PPN) and an auxiliary prediction network (APN). The framework can build the relationship between the geometric parameters of metamaterials and their optical response (reflection spectra, absorption spectra) from a large number of training samples, thus solving the problem of time-consuming and case-by-case numerical simulations in traditional metamaterial design. This framework can not only improve forward prediction more accurately and efficiently but also inverse design metamaterial absorbers from a given required optical response. It was verified that it is also applicable to absorbers of different structures and materials. Our results show that it can be used in metamaterial absorbers, chiral metamaterials, metamaterial filters, and other fields. [ABSTRACT FROM AUTHOR]

In recent years, significant progress has been made in the research of metamaterial perfect absorbers for on-demand design based on deep learning methods, and how to improve the generalization ability and prediction accuracy of network models in inverse design has been a hot topic of recent research. In this paper, we propose a fully connected neural network (RFC-NN) based on the residual principle applied to the inverse design of perfect absorbers. We design the RFC-NN model by applying the residual network structure commonly used on convolutional neural networks to a fully connected neural network, and the regression coefficients of the predicted structural parameters and the corresponding absorption spectra in the inverse design are 0.988 and 0.923, respectively, which have better prediction performance and generalization ability than the ordinary fully connected neural network (FC-NN), tandem neural network (TNN), and one-dimensional residual convolutional neural network (1D-Resnet). Then, we successfully designed the metamaterial perfect absorber with an absorption bandwidth (the spectral range where the absorptivity is greater than 90%) of 1935 nm using the trained RFC-NN model, which corresponds to an average absorptivity of 93.70%. Meanwhile, we use the analysis method of the Pearson correlation coefficient to improve the accuracy of the RFC-NN model after inverse design. Our proposed design method proves to be very effective and can also be applied to the design of other types of functional nanophotonic devices. • We realize forward prediction and inverse design of perfect absorber based on deep learning. In the inverse design, we propose a fully connected neural network (RFC-NN) based on the residual principle, which is more accurate than the traditional neural network in the inverse design. • Using the trained RFC-NN model, we successfully perform the on-demand design of perfect absorbers with large absorption bandwidth. • We use Pearson's correlation coefficient to analyze the relationship between the structural parameters of the perfect absorber and the absorption spectrum and use the relationship between them to improve the accuracy of the RFC-NN model in inverse design. [ABSTRACT FROM AUTHOR]

Slow light devices have important applications in many fields such as optical communication, optical storage, optical signal shaping and synchronization. Although a variety of high-performance slow light devices can be purchased in the market, it is still a worthwhile research topic to design slow light devices according to specific wavelengths and requirements. Here we employ machine learning method to inverse design electromagnetically induced transparency (EIT) based slow light devices in communication band using metal–dielectric hybrid metamaterials. Three characteristic points of transmittance as well as the group refractive index and bandwidth are chosen as input parameters. By replacing the complex fully connected layer with a one-dimensional convolutional neural network (1DCNN) layer to optimize the fully connected network, the proposed model can break the limitation of passive modulation and find the best slow light structure parameters. The slow light parameters could reach a bandwidth of 38.71 nm and average group refractive index of 10.51. In addition, the model can predict hybrid metamaterial structure parameters of slow light devices in the communication band from 1400 nm to 1600 nm. By combining active and passive modulation technologies, our proposed method improves the adjustment range of design parameters of slow light devices. The procedure can be potentially applied in the design of other nano optical devices. • The proposed model can find the optimal slow light structure parameters by utilizing a 1D convolutional neural network (1DCNN) layer to optimize the fully connected network. • By the prediction of the model, the slow light parameters could reach a bandwidth of 38.71 nm and average group refractive index of 10.51 in our metamaterial. • The model can predict hybrid metamaterial structure parameters of slow light devices in the communication band from 1400 nm to 1600 nm. [ABSTRACT FROM AUTHOR]