Thickness and index measurement of transparent thin films using neural network processed reflectance data

Abstract

Artificial neural networks and the Levenberg–Marquardt algorithm are combined to calculate the thickness and refractive index of transparent thin films from spectroscopic reflectometry data. A neural network is a set of simple, highly interconnected processing elements imitating the activity of the brain, which are capable of learning information presented to them. Reflectometry has been used by the semiconductor industry to measure thin film thickness for decades. Modeling the optical constants of a film in the visible region with a Cauchy dispersion model allows the determination of both thickness and refractive index of most transparent thin films from reflectance data. In this work, artificial neural networks are used to obtain good initial estimates for thickness and two Cauchy parameters An and Bn, these estimates are then used as the starting point for the Levenberg–Marquardt algorithm which converges to the final solution in a few iterations. This measurement program was implemented on a Nanometrics NanoSpec 8000XSE and will measure thickness and index of transparent films. The program works with a thickness range of 1000–16000 Å and index range of 1.36–2.35, and takes an average of 4 s.