Machine learning based virtual sensing of wafer temperatures during reflow process in a physical vapor deposition chamber with uncertain chamber physical properties and varying operating conditions

A method for determining a temperature of a substrate during processing, comprising:

• using proper orthogonal decomposition to extract modes from a virtual model of thermal conditions within a processing chamber, wherein the virtual model is created based on measuring temperature values associated with substrate processing, wherein a position of a target substrate is provided as an input to the virtual model;
• receiving thermal sensor data associated with the target substrate, wherein the thermal sensor data comprises a temperature measurement as a function of time;
• generating a thermal map for the target substrate based providing the thermal sensor data and the extracted modes as inputs to a compressed sensing algorithm;
• and
• performing one or more actions relating to processing substrates based on the thermal map.

A computer readable medium, storing instructions that when executed by a processor of a system, cause the system to:

• extract modes from a virtual model of thermal conditions within a processing chamber;
• receive thermal sensor data associated with a target substrate;
• and
• use compressed sensing to generate a thermal map for the target substrate
• based on the thermal sensor data and the extracted modes.