Abstract: Model optimization approaches based on spectral sensitivity is described. For example, a method includes determining a first model of a structure. The first model is based on a first set of parameters. A set of spectral sensitivity variations data is determined for the structure. Spectral sensitivity is determined by derivatives of the spectra with respect to the first set of parameters. The first model of the structure is modified to provide a second model of the structure based on the set of spectral sensitivity variations data. The second model of the structure is based on a second set of parameters different from the first set of parameters. A simulated spectrum derived from the second model of the structure is then provided.

Abstract: Methods of library generation with derivatives for optical metrology are described. For example, a method of generating a library for optical metrology includes determining a function of a parameter data set for one or more repeating structures on a semiconductor substrate or wafer. The method also includes determining a first derivative of the function of the parameter data set. The method also includes providing a spectral library based on both the function and the first derivative of the function.

Abstract: Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described.