Fast pattern design of the metasurface absorber based on deep learning and genetic algorithm

Abstract Metasurfaces capable of realizing complex electromagnetic responses provide new design routes to microwave absorption. The traditional optimization process for metasurface is time-consuming and computationally resource-consuming. With the help of advanced deep learning methods, the design of metasurfaces can be accelerated. In this paper, a trained residual neural network model is combined with an adjusted genetic algorithm to effectively reduce the optimization time of the metasurface pattern and structural parameters, thereby achieving a broadband effective absorption. The trained residual neural network has good prediction ability, with 99.48% of the test set samples having a loss value below 5 × 10 −5 ; the adjusted genetic algorithm is more effective in searching the potential space where the metasurface pattern is located. The optimal metasurface absorber covers the frequency range from 7.83 to 18.0 GHz (EAB 10.17 GHz) with a thickness of 3.97 mm. The combination of deep neural networks and optimization algorithm provides an effective way for the fast design of metasurface absorbers.