Machine Learning-Based Surrogate Modelling of Reflectarray Unit Cell in a 4-D Parallelotope-Shaped Domain

Abstract

A novel strategy to define a high-dimensionality parallelotope-shaped domain is proposed to train surrogate models of reflectarray unit cells. The concept is based on the definition of a region or rectangle of stability where sharp resonances are avoided as much as possible. Then, a 4-D parallelotope is defined around the rectangle of stability, controlling its size in order to avoid new resonances that appear as a consequence of increasing the dimensionality of the domain. This methodology is applied to generate surrogate models of a multi-resonant unit cell based on support vector regression. Results show a high degree of agreement between the obtained surrogate models and simulations based on the method of moments based on local periodicity tool that was used to generate the training samples. Furthermore, the proposed method performs better than lower dimensionality methods for wideband optimization.