Systems and methods for predicting film thickness of individual layers using virtual metrology
A method includes obtaining sensor data associated with a deposition process performed in a process chamber to deposit a film stack on a surface of a substrate, wherein the film stack comprises a plurality of layers of a first material and a plurality of layers of a second material. The method further includes obtaining metrology data associated with the film stack. The method further includes training a first machine-learning model based on the sensor data and the metrology data, wherein the first machine-learning model is trained to generate predictive metrology data associated with layers of the first material. The method further includes training a second machine-learning model based on the sensor data and the metrology data, wherein the second machine-learning model is trained to generate predictive metrology data associated with layers of the second material.
1. A method comprising:
obtaining, by a processor, sensor data associated with a deposition process performed in a process chamber to deposit a film stack on a surface of a substrate, wherein the film stack comprises a plurality of layers of a first material and a plurality of layers of a second material;
obtaining metrology data associated with the film stack;
training a first machine-learning model based on the sensor data and the metrology data, wherein the first machine-learning model is trained to generate predictive metrology data associated with layers of the first material; and
training a second machine-learning model based on the sensor data and the metrology data, wherein the second machine-learning model is trained to generate predictive metrology data associated with layers of the second material.
2. The method of claim 1 , further comprising:
updating the first machine-learning model and the second machine learning model based on a comparison between the predictive metrology data and measured metrology data.
3. The method of claim 2 , wherein the predictive metrology data comprise predictive mass data and the measured metrology data comprises measured mass data.
4. The method of claim 1 , wherein the metrology data comprises a measured thickness of an aggregated stack of a single material.
5. The method of claim 1 , wherein the metrology data comprises thickness data obtained from a Transmission Electron Microscope (TEM) analysis.
6. The method of claim 1 , wherein the metrology data comprises a measured thickness of the film stack.
7. The method of claim 1 , wherein the first material comprises oxide and the second material comprises nitride.
8. The method of claim 1 , further comprising:
determining, using the first machine-learning model and the second machine-learning model, predictive metrology data for a current substrate undergoing a current deposition process.
9. The method of claim 8 , further comprising:
adjusting a deposition process recipe associated with the current deposition process based on the predictive metrology data.
10. 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 a film stack on a surface of a substrate, wherein the film stack comprises a plurality of layers of a first material and a plurality of layers of a second material;
obtain metrology data associated with the film stack;
train a first machine-learning model based on the sensor data and the metrology data, wherein the first machine-learning model is trained to generate predictive metrology data associated with layers of the first material; and
train a second machine-learning model based on the sensor data and the metrology data, wherein the second machine-learning model is trained to generate predictive metrology data associated with layers of the second material.
11. The system of claim 10 , wherein the processing device is further to:
update the first machine-learning model and the second machine-learning model based on a comparison between the predictive metrology data and measured metrology data.
12. The system of claim 11 , wherein the predictive metrology data comprise predictive mass data and the measured metrology data comprises measured mass data.
13. The system of claim 10 , wherein the metrology data comprises a measured thickness of an aggregated stack of a single material.
14. The system of claim 10 , wherein the metrology data comprises thickness data obtained from a Transmission Electron Microscope (TEM) analysis.
15. The system of claim 10 , wherein the metrology data comprises a measured thickness of the film stack.
16. The system of claim 10 , wherein the first material comprises oxide and the second material comprises nitride.
17. The system of claim 10 , wherein the processing device is further to:
determine, using the first machine-learning model and the second machine-learning model, predictive metrology data for a current substrate undergoing a current deposition process.
18. The system of claim 17 , wherein the processing device is further to:
adjust a deposition process recipe associated with the current deposition process based on the predictive metrology data.
19. A non-transitory machine-readable storage medium storing instructions which, when executed cause a processing device to perform operations comprising:
obtaining, by a processor, sensor data associated with a deposition process performed in a process chamber to deposit a film stack on a surface of a substrate, wherein the film stack comprises a plurality of layers of a first material and a plurality of layers of a second material;
obtaining metrology data associated with the film stack;
training a first machine-learning model based on the sensor data and the metrology data, wherein the first machine-learning model is trained to generate predictive metrology data associated with layers of the first material; and
training a second machine-learning model based on the sensor data and the metrology data, wherein the second machine-learning model is trained to generate predictive metrology data associated with layers of the second material.
20. A method comprising:
obtaining a plurality of sensor values associated with a deposition process performed in a process chamber to deposit layers of film on a surface of a substrate;
applying a first machine-learning model to a first subset of the plurality of sensor values, the first machine-learning model trained based on historical sensor data and metrology data associated with layers of a first material;
applying a second machine-learning model to a second subset of the plurality of sensor values, the second machine-learning model trained based on the historical sensor data and metrology data associated with layers of a second material;
obtaining a first output of the first machine-learning model, the first output indicating first predictive metrology data for layers of the first material of the film; and
obtaining a second output of the second machine-learning model, the second output indicating second predictive metrology data for layers of the second material of the film.