Neural network design of broadband epsilon near zero perfect optical absorbers

Abstract

Research into epsilon near zero (ENZ) materials has enhanced the capabilities of metastructures, leading to unique optical properties such as perfect light absorption, non-reciprocal magneto-optical effects, and large optical nonlinearity. By constructing multilayer ENZ thin films, broadband ENZ properties and perfect absorption can be achieved. However, a critical challenge in developing broadband ENZ metastructures is the complex design of ENZ multilayer stack or heterostructure involving different physical parameters such as ENZ wavelength, thicknesses, optical losses, carrier concentrations, and material options. This work demonstrates the first use of a residual generative neural network to optimize broadband and perfect absorption properties of ultrathin ENZ materials, resulting in multi-stack ENZ layers with a maximum absorption above 99% over a bandwidth hundreds of nanometers wide.