Abstract: A method of predicting virtual metrology data for a wafer lot that includes receiving first image data from an imager system, the first image data relating to at least one first wafer lot, receiving measured metrology data from metrology equipment relating to the at least one first wafer lot, applying one or more machine learning techniques to the first image data and the measured metrology data to generate at least one predictive model for predicting at least one of virtual metrology data or virtual cell metrics data of wafer lots, and utilizing the at least one generated predictive model to generate at least one of first virtual metrology data or first virtual cell metrics data for the first wafer lot.

Abstract: Methods for optimizing petroleum reservoir analysis and sampling using a real-time component wherein heterogeneities in fluid properties exist. The methods help predict the recovery performance of oil such as, for example, heavy oil, which can be adversely impacted by fluid property gradients present in the reservoir. Additionally, the methods help optimize sampling schedules of the reservoir, which can reduce overall expense and increase sampling efficiency. The methods involve the use of analytical techniques for accurately predicting one or more fluid properties that are not in equilibrium in the reservoir. By evaluating the composition of downhole fluid samples taken from the reservoir using sensitive analytical techniques, an accurate base model of the fluid property of interest can be produced. With the base model in hand, real-time data can be obtained and compared to the base model in order to further define the fluid property of interest in the reservoir.