The design of multilayer ENZ stacks is challenging due to the many parameters involved, including the number of layers, thicknesses, ENZ wavelength, and optical losses. Our machine learning-based approach enables us to efficiently search through the vast design space and experimentally verify the performance of the resulting thin film stack. The resulting 2-layered AZO ENZ thin film stack achieved perfect absorption of light (> 95%) in the near-infrared region from 1500 nm to 2500 nm, highlighting the potential of machine learning techniques in designing ENZ materials for a range of applications.
|