Inverse Design of Electromagnetic Induced Transparency Metamaterials Based on Generative Adversarial Network

The unique properties of electromagnetic induced transparency (EIT) metamaterials have caused a lot of concern in the field of terahertz wave regulation, but the traditional design methods of metamaterials have the problems of long design cycle and high trial and error cost. Applying deep learning method to the inverse design process of terahertz metamaterials can greatly reduce the design complexity, so that the EIT metamaterial structure can be quickly designed according to the requirements. In this paper, a generative adversarial network (GAN) model for EIT metamaterial structure design is constructed, which realizes the mapping relationship between target spectrum and metamaterial structure parameters. The proposed GAN model can accurately predict structure parameters of the EIT metamaterial according to the target spectrum, and the error between the generated and the real parameters is less than 1μm. Moreover, by introducing the fuzzy processing, the proposed GAN model can accurately generate multiple sets of metamaterial structure according to the same target spectrum, which provides more options for designers. This model offers a novel and efficient design method for EIT metamaterials.