Systems and methods for predicting film thickness using virtual metrology
A method includes obtaining sensor data associated with a deposition process performed in a process chamber to deposit film on a surface of a substrate. The method further includes generating a plurality of physics based outputs using a transformation function and the sensor data. The method further includes mapping the physics based outputs to a training set. The method further includes training a virtual model based on the training set and the sensor data, wherein the virtual model is trained to generate predictive metrology data associated with the film.
1. A method comprising:
obtaining sensor data associated with a deposition process performed in a process chamber to deposit film on a surface of a substrate;
generating a plurality of physics based outputs using a transformation function and the sensor data, wherein the transformation function comprises functions associated with at least one of chemical kinetics or Langmuir adsorption model;
mapping the physics based outputs to a training set; and
training a virtual model based on the training set and the sensor data, wherein the virtual model is trained to generate predictive metrology data associated with the film.
2. The method of claim 1 , further comprising:
updating the virtual model based on a comparison between the predictive metrology data and measured metrology data.
3. The method of claim 1 , wherein the transformation function comprises functions associated with Arrhenius Equation.
4. The method of claim 1 , further comprising:
using the transformation function to compute a Maxwell distribution function for the process chamber.
5. The method of claim 1 , further comprising:
using the transformation function to estimate site availability for growth at equilibrium condition for the process chamber.
6. The method of claim 1 , further comprising:
using the transformation function to estimate boundary layer thickness in an equilibrium condition for the process chamber.
7. The method of claim 1 , further comprising:
determining, using the virtual model, real-time predictive metrology data for a current substrate undergoing a current deposition process.
8. The method of claim 7 , further comprising:
adjusting a deposition process recipe associated with the current deposition process based on the real-time predictive metrology data.
9. A system comprising:
a memory; and
a processing device, coupled to the memory, to:
obtain sensor data associated with a deposition process performed in a process chamber to deposit film on a surface of a substrate;
generate a plurality of physics based outputs using a transformation function and the sensor data, wherein the transformation function comprises functions associated with at least one of chemical kinetics or Langmuir adsorption model;
map the physics based outputs to a training set; and
train a virtual model based on the training set and the sensor data, wherein the virtual model is trained to generate predictive metrology data associated with the film.
10. The system of claim 9 , wherein the processing device is further to:
update the virtual model based on a comparison between the predictive metrology data and measured metrology data.
11. The system of claim 9 , wherein the transformation function comprises functions associated with Arrhenius Equation.
12. The system of claim 9 , wherein the processing device is further to:
use the transformation function to compute a Maxwell distribution function for the process chamber.
13. The system of claim 9 , wherein the processing device is further to:
use the transformation function to estimate site availability for growth at equilibrium condition for the process chamber.
14. The system of claim 9 , wherein the processing device is further to:
use the transformation function to estimate boundary layer thickness in an equilibrium condition for the process chamber.
15. The system of claim 9 , wherein the processing device is further to:
determine, using the virtual model, real-time predictive metrology data for a current substrate undergoing a current deposition process, and
adjust a deposition process recipe associated with the current deposition process based on the real-time predictive metrology data.
16. A non-transitory machine-readable storage medium storing instructions which, when executed cause a processing device to perform operations comprising:
obtaining sensor data associated with a deposition process performed in a process chamber to deposit film on a surface of a substrate;
generating a plurality of physics based outputs using a transformation function and the sensor data, wherein the transformation function comprises functions associated with at least one of chemical kinetics or Langmuir adsorption model;
mapping the physics based outputs to a training set; and
training a virtual model based on the training set and the sensor data, wherein the virtual model is trained to generate predictive metrology data associated with the film.
17. A method comprising:
obtaining a plurality of sensor values associated with a deposition process performed in a process chamber to deposit film on a surface of a substrate;
applying a virtual model to the plurality of sensor values, the virtual model trained based on historical sensor data and a plurality of physics based outputs used to process non-linear relationships between the historical sensor data from different sensors in the process chamber, wherein the plurality of physics based outputs were generated using a transformation function and the historical sensor data, wherein the transformation function comprises functions associated with at least one of chemical kinetics or Langmuir adsorption model; and
obtaining an output of the virtual model, the output identifying predictive metrology data for the film.
18. The method of claim 17 , wherein the predictive metrology data comprises a contour map including a set of spatial measurements each indicating a thickness of a particular location of a plurality of locations on the substrate.
19. The method of claim 17 , wherein the predictive metrology data indicates an average predictive film thickness.
20. The method of claim 17 , wherein the transformation function comprises functions associated with Arrhenius Equation.
21. The method of claim 17 , wherein the transformation function is used to compute a Maxwell distribution function for the process chamber.
22. The method of claim 17 , wherein the transformation function is used to estimate site availability for growth at equilibrium condition for the process chamber.
23. The method of claim 17 , wherein the transformation function is used to estimate boundary layer thickness in an equilibrium condition for the process chamber.