Using Gaussian process regression for effcient parameter reconstruction

摘要

Optical scatterometry is a method to measure the size and shape of periodic micro- or nanostructures on surfaces.For this purpose the geometry parameters of the structures are obtained by reproducing experimental measurementresults through numerical simulations. We compare the performance of Bayesian optimization to differentlocal minimization algorithms for this numerical optimization problem. Bayesian optimization uses Gaussianprocessregression to find promising parameter values. We examine how pre-computed simulation results can beused to train the Gaussian process and to accelerate the optimization.