Optical metrology in machine learning to characterize features

1. A method of determining a profile, critical dimension, and/or contour of one or more features on a processed substrate, the method comprising:

performing optical metrology on the one or more features on the processed substrate to produce an optical metrology output;

providing the optical metrology output to a metrology machine learning model that has been trained using a training set of (i) profiles, critical dimensions, and/or contours for a plurality of features, and (ii) optical metrology outputs for said plurality of features; and

receiving, from the metrology machine learning model, the profile, critical dimension, and/or contour of the one or more features on the processed substrate.

2. The method of claim 1 , further comprising training the metrology machine learning model by producing multiple sets of optical metrology output, each generated for a different orientation and/or location of test features with respect an optical metrology apparatus, for said test features.

3. The method of claim 1 , wherein the optical metrology is a scatterometry technique.

4. The method of claim 1 , wherein the optical metrology output comprises a reflectance spectra.

5. The method of claim 1 , wherein the optical metrology output comprises ellipsometric output data.

6. The method of claim 1 , further comprising:

performing pattern recognition on the one or more features on the processed substrate; and

determining that a pattern of the one or more features conforms with an expected pattern.

7. The method of claim 1 , wherein performing optical metrology on the one or more features on the processed substrate comprises raster scanning over the processed substrate.

8. The method of claim 1 , wherein the profiles, critical dimensions, and/or contours for a plurality of features in the training set were obtained using an electron microscopy technique.

9. The method of claim 1 , wherein the profiles, critical dimensions, and/or contours for a plurality of features in the training set were obtained using CD-SAXS.

10. The method of claim 1 , wherein the metrology machine learning model was produced using a supervised machine learning technique.

11. The method of claim 1 , further comprising decomposing the optical metrology output to produce a reduced set of optical metrology values and providing said reduced set of optical metrology values to the metrology machine learning model.

12. The method of claim 11 , wherein decomposing the optical metrology output comprises identifying principal components of the optical metrology output or applying the optical metrology output to an autoencoder.

13. A metrology system comprising:

an optical metrology tool comprising an optical probe source and an optical detector and a processor configured to produce an optical metrology output from data produced by the optical detector when an optical probe is directed onto one or more features on a processed substrate; and

a metrology machine learning model that has been trained using a training set of (i) profiles, critical dimensions, and/or contours for a plurality of features, and (ii) optical metrology outputs for said plurality of features, wherein the metrology machine learning model is configured to:

receive the optical metrology output from the optical metrology tool; and

output the profile, critical dimension, and/or contour of the one or more features on the processed substrate.

14. The metrology system of claim 13 , wherein the metrology machine learning model was trained using multiple sets of optical metrology output, each generated for a different orientation and/or location of test features with respect a test optical metrology apparatus.

15. The metrology system of claim 13 , wherein the optical metrology tool is a scatterometer.

16. The metrology system of claim 13 , wherein the optical metrology output comprises a reflectance spectra.

17. The metrology system of claim 13 , wherein the optical metrology output comprises ellipsometric output data.

18. The metrology system of claim 13 , further comprising a pattern recognition tool comprising a camera and processor configured to:

perform pattern recognition on the one or more features on the processed substrate; and

determine that a pattern of the one or more features conforms with an expected pattern.

19. The metrology system of claim 13 , wherein the optical metrology tool is configured to raster scan over the processed substrate.

20. The metrology system of claim 13 , wherein the profiles, critical dimensions, and/or contours for a plurality of features in the training set were obtained using an electron microscopy technique.

21. The metrology system of claim 13 , wherein the profiles, critical dimensions, and/or contours for a plurality of features in the training set were obtained using CD-SAXS.

22. The metrology system of claim 13 , wherein the metrology machine learning model was generated using a supervised machine learning technique.

23. The metrology system of claim 13 , wherein the metrology machine learning model is further configured to: decompose the optical metrology output to produce a reduced set of optical metrology values and provide said reduced set of optical metrology values to the metrology machine learning model.

24. The metrology system of claim 23 , wherein the metrology machine learning model is configured to decompose the optical metrology output by identifying principal components of the optical metrology output or by applying the optical metrology output to an autoencoder.