Prediction data selection for model calibration to reduce model prediction uncertainty

Patent metadata

Field	Value
Publication number	US-12443111-B2
Application number	US-202017625125-A
Country	US
Kind code	B2
Filing date	Jun 15, 2020
Priority date	Jul 10, 2019
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

Systems and methods for reducing prediction uncertainty in a prediction model associated with a patterning process are described. These may be used in calibrating a process model associated with the patterning process, for example. Reducing the uncertainty in the prediction model may include determining a prediction uncertainty parameter based on prediction data. The prediction data may be determined using the prediction model. The prediction model may have been calibrated with calibration data. The prediction uncertainty parameter may be associated with variation in the prediction data. Reducing the uncertainty in the prediction model may include selecting a subset of process data based on the prediction uncertainty parameter; and recalibrating the prediction model using the calibration data and the selected subset of the process data.

First claim

What is claimed is:

1. A method comprising:
determining, by a hardware computer system, prediction data using one or more the prediction models, the one or more prediction models having been calibrated with calibration data;
determining a prediction uncertainty parameter based on the prediction data, the prediction uncertainty parameter associated with variation in the prediction data;
selecting, based on the prediction uncertainty parameter, a set of data associated with a patterning process; and
using the set of data to enable configuration of a prediction model that produces, in use, less uncertain or more accurate prediction data.

2. The method of claim 1 , wherein the set of data comprises a subset of patterning process data.

3. The method of claim 2 , wherein the using comprises recalibrating the prediction model using the calibration data and the selected subset of the patterning process data.

4. The method of claim 3 , further comprising determining one or more semiconductor device manufacturing process parameters based on a prediction from the recalibrated prediction model.

5. The method of claim 4 , wherein the one or more determined semiconductor device manufacturing process parameters comprise a mask design, and
further comprising adjusting the mask design from a first mask design to a second mask design based on the prediction from the recalibrated prediction model.

6. The method of claim 4 , further comprising iteratively repeating the determining prediction data, the determining the prediction uncertainty parameter, the selecting, and the recalibrating until the recalibrated prediction model converges.

7. The method of claim 6 , wherein model convergence is indicated by a model error breaching a model error threshold level, the model error being a difference between a reference geometry and a simulated geometry generated from a simulation of the patterning process by the recalibrated prediction model.

8. The method of claim 7 , wherein the reference geometry is a measured geometry from a scanning electron microscope.

9. The method of claim 1 , wherein the prediction uncertainty parameter is associated with at least one selected from:
a value of critical dimension of a substrate;
a curvature associated with a pattern of the patterning process;
an intensity used in the patterning process; or
an image slope associated with a pattern of the patterning process.

10. The method of claim 1 , further comprising determining one or more semiconductor device manufacturing process parameters based on the selected data, wherein the one or more determined semiconductor device manufacturing process parameters comprise one or more selected from: a mask design, design patterns, a pupil shape, a dose, or a focus.

11. The method of claim 1 , wherein the selecting the set of data comprises selecting a set of patterns.

12. The method of claim 11 , wherein the using comprises using the selected set of patterns to train or calibrate a prediction model that is a machine learning model or a non-machine learning model.

13. The method of claim 1 , further comprising:
determining one or more semiconductor device manufacturing process parameters based on the selected data; and
determining an adjustment for a semiconductor device manufacturing apparatus based on the one or more determined semiconductor device manufacturing parameters.

14. The method of claim 1 , further comprising:
determining one or more semiconductor device manufacturing process parameters based on the selected data; and
determining an adjustment for a semiconductor device manufacturing process based on the one or more determined semiconductor device manufacturing parameters.

15. The method of claim 1 , wherein the calibration data comprises a calibration pattern, the calibration pattern associated with geometrical features of a pattern on a substrate, and wherein the prediction data comprises a prediction pattern, the prediction pattern associated with predicted geometrical features of the pattern on the substrate.

16. The method of claim 15 , wherein the selecting the set of data comprises selecting a set of patterns.

17. A non-transitory computer-readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:
determining, by a hardware computer system, prediction data using one or more prediction models, the one or more prediction models having been calibrated with calibration data;
determining a prediction uncertainty parameter based on the prediction data, the prediction uncertainty parameter associated with variation in the prediction data; and
selecting, based on the prediction uncertainty parameter, a set of data associated with a patterning process; and
use the set of data to enable configuration of a prediction model that produces, in use, less uncertain or more accurate prediction data.

18. The medium of claim 17 , wherein the set of data comprises a subset of patterning process data.

19. The medium of claim 18 , wherein the instructions configured to cause the computer system to use the set of data are further configured to cause the computer system to recalibrate a prediction model using the calibration data and the selected subset of the patterning process data.

20. The medium of claim 19 , wherein the instructions are further configured to cause the computer system to determine one or more semiconductor device manufacturing process parameters based on a prediction from the recalibrated prediction model.

Assignees

• Asml Netherlands Bv
• Asml Netherlands

Inventors

• Wang Lei
• Chen Yi-Yin
• Feng Mu
• Zhao Qian

Classifications

• G03F7/706839

  Modelling, e.g. modelling scattering or solving inverse problems · CPC title

• G03F1/68

  Preparation processes not covered by groups G03F1/20 - G03F1/50 · CPC title

• G03F1/36

  Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction [OPC] design processes · CPC title

• G03F7/70625

  Dimensions, e.g. line width, critical dimension [CD], profile, sidewall angle or edge roughness · CPC title

• G03F7/705 Primary

  Modelling or simulating from physical phenomena up to complete wafer processes or whole workflow in wafer productions · CPC title