Determining a correction to a process
A method for configuring a semiconductor manufacturing process, the method including: 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 and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.
1 . A method comprising:
obtaining first sparse data representing measured values of a parameter across one or more substrates subject to a process and measured using a sparse sampling layout;
obtaining dense data representing measured values of the parameter across one or more substrates subject to the process and measured using a dense sampling layout that is more spatially dense than the sparse sampling layout;
applying a model to the sparse data and dense data to determine a sparse-to-dense mismatch;
adapting the model based on the sparse-to-dense mismatch;
obtaining second sparse data representing measured values of the parameter across one or more substrates subject to the process and measured using a sparse sampling layout;
applying the adapted model to the second sparse data to determine a sparse model result; and
determining a correction to the process based on the sparse model result.
2 . The method of claim 1 , wherein the adapting the model based on the sparse-to-dense mismatch comprises:
evaluating different contributions of respective parts of the model to the sparse-to-dense mismatch;
determining weighting factors for weighting the respective parts of the model to reduce the sparse-to-dense mismatch; and
adapting the model with the weighting factors.
3 . The method of claim 2 , wherein the determining weighting factors comprises determining weighting factors for weighting the respective parts of the model to minimize the sparse-to-dense mismatch.
4 . The method of claim 1 , wherein the determining the sparse-to-dense mismatch comprises training a matrix on the first sparse data and the dense data, and further comprising modifying the second sparse data using the matrix.
5 . The method of claim 1 , wherein the obtaining second sparse data comprises obtaining second sparse data by downsampling second dense data representing measured values of the parameter across a plurality of substrates subject to the process, the dense data measured using different sparse sampling layouts distributed over the plurality of substrates.
6 . The method of claim 5 , wherein the sparse model result comprises sparse model residuals, the method further comprises applying the model to the sparse model residuals to determine a dense model result, and the determining a correction to the process is further based on the dense model result.
7 . The method of claim 1 , wherein the sparse model result comprises sparse model residuals, the method further comprises applying the model to the sparse model residuals to determine a dense model result, and the determining a correction to the process is further based on the dense model result.
8 . A semiconductor manufacturing process comprising:
manufacturing a semiconductor; and
performing the method according to claim 1 .
9 . A lithographic apparatus comprising:
a support structure configured to support a patterning device, the patterning device configured to pattern a beam of radiation according to a desired pattern;
a substrate table configured to hold a substrate;
a projection system configured the project the patterned beam onto a target portion of the substrate; and
a processing unit configured to perform the method of claim 1 .
10 . A lithographic cell comprising the lithographic apparatus of claim 9 .
11 . A computer program product comprising a non-transitory computer-readable medium comprising instructions therein, the instructions, upon execution by a computer system, configured to cause the computer system to at least:
obtain first sparse data representing measured values of a parameter across one or more substrates subject to a process and measured using a sparse sampling layout;
obtain dense data representing measured values of the parameter across one or more substrates subject to the process and measured using a dense sampling layout that is more spatially dense than the sparse sampling layout;
apply a model to the sparse data and dense data to determine a sparse-to-dense mismatch;
adapt the model based on the sparse-to-dense mismatch;
obtain second sparse data representing measured values of the parameter across one or more substrates subject to the process and measured using a sparse sampling layout;
apply the adapted model to the second sparse data to determine a sparse model result; and
determine a correction to the process based on the sparse model result.
12 . The computer program product of claim 11 , wherein the instructions configured to cause the computer system to adapt the model are further configured to cause the computer system to:
evaluate different contributions of respective parts of the model to the sparse-to-dense mismatch;
determine weighting factors for weighting the respective parts of the model to reduce the sparse-to-dense mismatch; and
adapt the model with the weighting factors.
13 . The computer program product of claim 12 , wherein the instructions configured to cause the computer system to determine the weight factors are further configured to cause the computer system to determine weighting factors for weighting the respective parts of the model to minimize the sparse-to-dense mismatch.
14 . The computer program product of claim 11 , wherein the instructions are further configured to cause the computer system to:
train a matrix on the first sparse data and the dense data, and
modify the second sparse data using the matrix.
15 . The computer program product of claim 11 , wherein the instructions configured to cause the computer system to obtain second sparse data are further configured to cause the computer system to obtain second sparse data by downsampling second dense data representing measured values of the parameter across a plurality of substrates subject to the process, the dense data measured using different sparse sampling layouts distributed over the plurality of substrates.
16 . The computer program product of claim 15 , wherein the sparse model result comprises sparse model residuals and wherein the instructions are further configured to cause the computer system to apply the model to the sparse model residuals to determine a dense model result, and further determine the correction to the process based on the dense model result.
17 . The computer program product of claim 11 , wherein the sparse model result comprises sparse model residuals and wherein the instructions are further configured to cause the computer system to apply the model to the sparse model residuals to determine a dense model result, and further determine the correction to the process based on the dense model result.
18 . The computer program product of claim 11 , wherein the parameter comprises overlay.
19 . A lithographic apparatus comprising:
a support structure configured to support a patterning device, the patterning device configured to pattern a beam of radiation according to a desired pattern;
a substrate table configured to hold a substrate;
a projection system configured the project the patterned beam onto a target portion of the substrate; and
the computer program product of claim 11 .
20 . A lithographic cell comprising the lithographic apparatus of claim 19 .