Abstract: Embodiments described herein include processes for generating a hybrid model for modeling processes in semiconductor processing equipment. In a particular embodiment, method of creating a hybrid machine learning model comprises identifying a first set of cases spanning a first range of process and/or hardware parameters, and running experiments in a lab for the first set of cases. The method may further comprise compiling experimental outputs from the experiments, and running physics based simulations for the first set of cases. In an embodiment, the method may further comprise compiling model outputs from the simulations, and correlating the model outputs with the experimental outputs with a machine learning algorithm to provide the hybrid machine learning model.

Abstract: Methods and apparatus for a PVD chamber are provided herein. In some embodiments, a selective PVD chamber includes a first housing surrounding a movable substrate support; a second housing adjacent the first housing; an opening disposed between the first housing and the second housing that partially exposes a top surface of the movable substrate support, wherein the opening includes a first curved side; and an elongate target disposed in the second housing to provide a stream of material flux from the elongate target into the first housing via the opening.