Methods of metrology

Patent metadata

Field	Value
Publication number	US-2025147436-A1
Application number	US-202318832408-A
Country	US
Kind code	A1
Filing date	Jan 23, 2023
Priority date	Feb 21, 2022
Publication date	May 8, 2025
Grant date	—

Abstract

A method for determining a parameter of interest relating to at least one structure formed on a substrate in a manufacturing process. The method includes: obtaining layout data relating to a layout of a pattern to be applied to the at least one structure, the pattern including the at least one structure; and obtaining a trained model, having been trained on metrology data and the layout data to infer a value and/or probability metric relating to a parameter of interest from at least the layout data, the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate. A value and/or probability metric is determined relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least layout data using the trained model.

First claim

1 . A method for determining a parameter of interest relating to at least one structure formed on a substrate in a manufacturing process, the method comprising:
obtaining layout data relating to a layout of a pattern to be applied to the at least one structure, the pattern comprising the at least one structure; obtaining a trained computer model, having been trained on metrology data and the layout data to infer a value and/or probability metric relating to the parameter of interest from at least the layout data, the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate; and determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model.

2 . The method as claimed in claim 1 , wherein the parameter of interest is overlay or edge placement error.

3 . The method as claimed in claim 1 , wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model.

4 . The method as claimed in claim 1 , wherein the metrology data comprises after develop inspection metrology data measured by a scatterometer.

5 . The method as claimed in claim 1 , wherein the metrology data comprises after etch inspection metrology data measured subsequent to an etching and/or a polishing step.

6 . The method as claimed in any of claim 1 , wherein the metrology data comprises connectivity e-test data or scanning electron microscope measurement data.

7 . The method as claimed in claim 1 , wherein the layout data comprises a pattern density spatial distribution.

8 . The method as claimed in claim 1 , wherein the determining comprises determining a spatial distribution of the parameter of interest over at least an exposure field.

9 . The method as claimed in claim 1 , wherein the determining uses substrate position data to determine a spatial distribution of the parameter of interest over the substrate, the trained model having been trained per-field based on the substrate location data.

10 . The method as claimed in claim 8 , further comprising using the spatial distribution of the parameter of interest to optimize one or more settings in the manufacturing process and/or identify one or more areas or structures for further inspection.

11 . The method as claimed in claim 1 , further comprising:
obtaining training layout data comprising a similar type of data as the layout data; obtaining training metrology data corresponding to the training layout data; and training a machine learning model with the training metrology data and dense layout data to obtain the trained model.

12 . The method as claimed in claim 11 , wherein the training metrology data comprises at least after-etch inspection metrology data measured subsequent to an etching and/or polishing step.

13 . The method as claimed in claim 12 , wherein the training metrology data further comprises after-develop inspection metrology data, and the training comprises training the machine learning model to interpolate a sparse sampling of after-develop inspection metrology data to a denser sampling of after-etch inspection metrology data.

14 . The method as claimed in claim 11 , wherein the layout data and training layout data comprise pattern density images.

15 . (canceled)

16 . 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:
obtaining layout data relating to a layout of a pattern to be applied to at least one structure formed on a substrate in a manufacturing process, the pattern comprising the at least one structure; obtaining a trained computer model, having been trained on metrology data and the layout data to infer a value and/or probability metric relating to a parameter of interest from at least the layout data, the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate; and determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model.

17 . The medium as claimed in claim 16 , wherein the parameter of interest is overlay or edge placement error.

18 . The medium as claimed in claim 16 , wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and the instructions configured to cause the computer system to determine a value and/or probability metric relating to the parameter of interest are configured to cause the computer system to determine the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model.

19 . The medium as claimed in claim 16 , wherein the instructions configured to cause the computer system to determine a value and/or probability metric relating to the parameter of interest are configured to cause the computer system to determine a spatial distribution of the parameter of interest over at least an exposure field.

20 . The medium as claimed in claim 16 , wherein the instructions configured to cause the computer system to determine a value and/or probability metric relating to the parameter of interest are configured to cause the computer system to use substrate position data to determine a spatial distribution of the parameter of interest over the substrate, the trained model having been trained per-field based on the substrate location data.

21 . The medium as claimed in claim 16 , wherein the instructions are further configured to cause the computer system to use the spatial distribution of the parameter of interest to optimize one or more settings in the manufacturing process and/or identify one or more areas or structures for further inspection.

Assignees

• Asml Netherlands Bv

Inventors

• Batistakis Chrysostomos
• Zhang Huaichen
• Pisarenco Maxim
• Bastani Vahid
• Nechaev Konstantin Sergeevich
• Anunciado Roy
• Van Der Sanden Stefan Cornelis Theodorus

Classifications

• G03F7/70625

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

• G03F7/70283

  Mask effects on the imaging process · CPC title

• G03F7/706831

  Recipe selection or optimisation, e.g. select or optimise recipe parameters such as wavelength, polarisation or illumination modes · CPC title

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G06N3/09

  Supervised learning · CPC title