General Inverse Design of Layered Thin-Film Materials with Convolutional Neural Networks
Andrew Lininger, Michael Hinczewski, Giuseppe Strangi
Abstract
The design of metamaterials which support unique optical responses is the basis for most thin-film nanophotonic applications. In practice, this inverse design (ID) problem can be difficult to solve systematically due to the large design parameter space associated with general multilayered systems. We apply convolutional neural networks, a subset of deep machine learning, as a tool to solve this ID problem for metamaterials composed of stacks of thin films. We demonstrate the remarkable ability of neural networks to probe the large global design space (up to 1012 possible parameter combinations) and resolve all relationships between the metamaterial structure and corresponding ellipsometric and reflectance/transmittance spectra. The applicability of the approach is further expanded to include the ID of synthetic engineered spectra in general design scenarios. Furthermore, this approach is compared with traditional optimization methods. We find an increase in the relative optimization efficiency of the networks with the increase in the total layer number, revealing the advantage of the machine learning approach in many-layered systems where traditional methods become impractical.