Virtual metrology

In semiconductor manufacturing, virtual metrology refers to methods to predict properties of a wafer based on machine parameters and sensor data of the production equipment, without performing the (costly) physical measurement of the wafer properties. Statistical methods such as classification and regression are used to perform such a task. An example is the prediction of the silicon nitride ($Si_3 N_4$) layer thickness in the chemical vapor deposition process (CVD), using multivariate regression methods.^[1]

References

1. Purwins, Hendrik; Bernd, Barak; Nagi, Ahmed; Engel, Reiner; Hoeckele, Uwe; Kyek, Andreas; Cherla, Srikanth; Lenz, Benjamin; Pfeifer, Guenther; Weinzierl, Kurt (2014). "Regression Methods for Virtual Metrology of Layer Thickness in Chemical Vapor Deposition". IEEE - ASME Transactions on Mechatronics 19 (1): 1–8. doi:10.1109/TMECH.2013.2273435.