PROCESS CONTROL USING RAY TRACING-BASED LIBRARIES AND MACHINE LEARNING SYSTEMS

Provided is a method for controlling a fabrication cluster comprising an optical metrology tool and an optical metrology model including a profile model of a sample structure, the optical metrology tool having an illumination beam, the illumination beam having a range of angles of incidence and azimuth angles. A library comprising Jones and/or Mueller matrices and/or components (JMMOC) and corresponding profile parameters is generated using ray tracing and a selected range of beam propagation parameters and can be used to train a machine learning system (MLS). A regenerated simulated diffraction signal is obtained with a regenerated JMMOC using the library or MLS, integrated for all the rays of the optical metrology model. One or more profile parameters are determined from the best match regenerated simulated diffraction signal. At least one process parameter of the fabrication cluster is adjusted based on the determined one or more profile parameters.