A deep learning approach for inverse design of the metasurface for dual-polarized waves

Compared to the conventional metasurface design, machine learning-based methods have recently created an inspiring platform for an inverse realization of the metasurfaces. Here, we have used the Deep Neural Network (DNN) for the generation of desired output unit cell structures for both TE and TM polarized waves which its working frequency can reach up to 45 GHz. To automatically generate metasurfaces over wide frequencies, we deliberately design 8 annular models; thus, each generated meta-atoms in our dataset can produce different notches in our desired working frequency. Compared to the general approach, whereby the final metasurface structure may be formed by any randomly distributed "0" and "1", we propose here a confined output configuration. By confining the output, the number of calculations will be decreased and the learning speed will be increased. Establishing a DNN-confined output configuration based on the input data for both TE and TM polarized waves is the novelty to generate the desired metasurface structure for dual orthogonal polarizations. Moreover, we have demonstrated that our network can attain an accuracy of 92%. Obtaining the final unit cell directly without any time-consuming optimization algorithms for both TE and TM polarized waves, and high average accuracy, open beneficial ways for the inverse metasurface design; thus, the designer is required only to focus on the design goal.