Virtual metrology

In semiconductor manufacturing, virtual metrology refers to methods to predict the properties of a wafer based on machine parameters and sensor data in 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.

Examples of virtual metrology include:

• the prediction of the silicon nitride ($Si_{3}N_{4}$) layer thickness in the chemical vapor deposition process (CVD), using multivariate regression methods;
• the prediction of critical dimension in photolithography, using multi-level and regularization approaches;
• the prediction of layer width in etching.