Determining a correction to a process

1. A method for configuring a semiconductor manufacturing process, the method comprising:

obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process;

using, by a hardware computer, a recurrent neural network to determine a predicted value of the first parameter based on use of the first value as an input to the recurrent neural network; and

using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

2. The method of claim 1 , wherein the measurements associated with the first operation of the process step are associated with a first sampling scheme and the method further comprises:

obtaining a value of a second parameter based on measurements using a second sampling scheme being spatially less dense than the first sampling scheme; and

using the value of the second parameter in configuring the subsequent operation of the process step in the semiconductor manufacturing process.

3. The method of claim 2 , wherein the value of the second parameter is obtained based on measurements at the subsequent operation of the process step.

4. The method of claim 3 , wherein the value of the second parameter is obtained based on measurements performed on the same substrate supported on the same substrate table at which the subsequent operation of the process step is performed with the subsequent operation of the process step being configured using the value of the second parameter.

5. The method of claim 2 , wherein the semiconductor manufacturing process is a batch-wise process of patterning substrates, and wherein the first sampling scheme has a measurement frequency of per 5 to 10 batches and the second sampling scheme has a measurement frequency of one per batch.

6. The method claim 2 , wherein the semiconductor manufacturing process is a process of patterning substrates using exposure fields, and wherein the first sampling scheme has a spatial density of 200 to 300 measurement points per exposure field and the second sampling scheme has a spatial density of 2 to 3 measurement points per exposure field.

7. The method of claim 1 , further comprising obtaining a subsequent value of the first parameter based on the measurements and updating the recurrent neural network using the subsequent value.

8. The method of claim 1 , wherein the recurrent neural network comprises a Long Short-Term Memory network.

9. A semiconductor manufacturing process comprising the method for configuring a semiconductor manufacturing process according to claim 1 .

10. The method of claim 1 , further comprising determining a value of a parameter associated with a model used by a controller of a semiconductor manufacturing process based on the predicted value of the first parameter and the obtained first value of the first parameter.

11. The method of claim 10 , wherein the determining is based on comparing the predicted value of the first parameter with a value of the first parameter obtained by application of the model to the obtained first value of the first parameter.

12. The method of claim 10 , wherein the model is an Exponentially Weighted Moving Averaging model and the parameter is a smoothing constant associated with the Exponentially Weighted Moving Averaging model.

13. A non-transitory computer program product comprising machine readable instructions, the instructions, when executed by a data processing apparatus, are configured to cause the data processing apparatus to at least:

obtain a first value of a first parameter based on measurements associated with a first operation of a process step in a semiconductor manufacturing process;

use a recurrent neural network to determine a predicted value of the first parameter based on use of the first value as an input to the recurrent neural network; and

use the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

14. The computer program product of claim 13 , wherein the recurrent neural network comprises a Long Short-Term Memory network.

15. The computer program product of claim 13 , wherein the instructions are further configured to cause the data processing apparatus to determine a value of a parameter associated with a model used by a controller of a semiconductor manufacturing process based on the predicted value of the first parameter and the obtained first value of the first parameter.

16. The computer program product of claim 15 , wherein the instructions configured to cause the data processing apparatus to determine the value of the parameter associated with the model are further configured to cause the data processing apparatus to determine the value of the parameter associated with the model based on a comparison of the predicted value of the first parameter with a value of the first parameter obtained by application of the model to the obtained first value of the first parameter.

17. The computer program product of claim 15 , wherein the model is an Exponentially Weighted Moving Averaging model.

18. A non-transitory computer program product comprising machine readable instructions, the instructions, when executed by a data processing apparatus, are configured to cause the data processing apparatus to at least:

obtain a first value of a first parameter based on measurements associated with a process step in a semiconductor manufacturing process;

use a recurrent neural network to determine a predicted value of the first parameter based on use of the first value as an input to the recurrent neural network; and

use the predicted value of the first parameter in configuring a controller used in run-to-run control of the semiconductor manufacturing process.

19. The computer program product of claim 18 , wherein the configuration of the controller comprises configuration of an Exponentially Weighted Moving Averaging model used in the run-to-run control of the semiconductor manufacturing process.

20. A method for configuring a semiconductor manufacturing process, the method comprising:

obtaining a first value of a first parameter based on measurements associated with a process step in the semiconductor manufacturing process;

using, by a hardware computer system, a recurrent neural network to determine a predicted value of the first parameter based on use of the first value as an input to the recurrent neural network; and

using the predicted value of the first parameter in configuring an Exponentially Weighted Moving Averaging model used in run-to-run control of the semiconductor manufacturing process.

21. The method of claim 20 , wherein the measurements associated with the process step are associated with a first sampling scheme and the method further comprises:

obtaining a value of a second parameter based on measurements using a second sampling scheme being spatially less dense than the first sampling scheme; and

using the value of the second parameter in run-to-run control of the semiconductor manufacturing process.

22. The method of claim 21 , wherein the value of the second parameter is obtained based on measurements at a subsequent operation in the semiconductor manufacturing process.

23. The method of claim 22 , wherein the value of the second parameter is obtained based on measurements performed on the same substrate supported on the same substrate table at which the subsequent operation is performed with the subsequent operation being configured using the value of the second parameter.

24. The method of claim 22 , wherein the recurrent neural network comprises a Long Short-Term Memory network.

25. A non-transitory computer program product comprising machine readable instructions therein, the instructions, when executed by a data processing apparatus, are configured to cause the data processing apparatus to at least perform the method of claim 20 .

26. The computer program product of claim 18 , wherein the measurements associated with the process step are associated with a first sampling scheme and the instructions are further configured to cause the data processing apparatus to:

obtain a value of a second parameter based on measurements using a second sampling scheme being spatially less dense than the first sampling scheme; and

use the value of the second parameter in run-to-run control of the semiconductor manufacturing process.

27. The computer program product of claim 26 , wherein the value of the second parameter is obtained based on measurements at a subsequent operation in the semiconductor manufacturing process.

28. The computer program product of claim 18 , wherein the recurrent neural network comprises a Long Short-Term Memory network.