A Machine Learning-Based Approach to Synthesize Multilayer Metasurfaces

The synthesis of a metasurface exhibiting a specific set of desired scattering properties is a time-consuming and resource-demanding process, which conventionally relies on many cycles of full-wave simulations. It requires the designer to choose the number of the metallic layers, the scatterer shapes, and the type and the thickness of the separating substrates. Here, we propose a machine learning (ML)-based approach to automate the inverse design of dual-layer metasurfaces, which is extendable to multilayer metasurfaces. This approach allows synthesis of thin structures where higher-order mode coupling between the layers is significant, and hence, can be leveraged for extra degrees of freedom.