Numerical ellipsometry: Artificial intelligence for rapid analysis of indium tin oxide films on silicon

Abstract

Ellipsometry is a well-known material analytical method widely used to measure thickness and optical properties of thin films and surfaces across a wide range of industrial and research applications including critical dimensions in chipmaking. The method employs the fact that light undergoes a change in polarization state upon reflection from or transmission through a material. The desired properties of the surface structure are related to measurements by the electromagnetic models expressed by Maxwell’s equations as well as models of material properties. The work here demonstrates the use of artificial intelligence in the form of a multilayer perceptron artificial neural network to apply the electromagnetic model. The reflecting surface examined here is composed of indium tin oxide (ITO) films approximately 400 nm in thickness deposited on silicon substrates. Solutions are provided by 299 artificial neural networks, one per wavelength from 210 to 1700 nm across which ITO exhibits transparent as well as absorbing characteristics. Thus, it serves as a proxy for a wide range of other materials. To train the network, simulated measurements are computed at two thicknesses which differ randomly by 1–6 nm and at three different incidence angles of 55°, 65°, and 75°. Following training, results are obtained in less than one second on a conventional desktop computer.