Method for determining a stochastic metric relating to a lithographic process

Patent metadata

Field	Value
Publication number	US-2024369944-A1
Application number	US-202218287166-A
Country	US
Kind code	A1
Filing date	Apr 12, 2022
Priority date	May 6, 2021
Publication date	Nov 7, 2024
Grant date	—

Abstract

A method of determining a stochastic metric, the method including: obtaining a trained model having been trained to correlate training optical metrology data to training stochastic metric data, wherein the training optical metrology data includes a plurality of measurement signals relating to distributions of an intensity related parameter across a zero or higher order of diffraction of radiation scattered from a plurality of training structures, and the training stochastic metric data includes stochastic metric values relating to the plurality of training structures, wherein the plurality of training structures have been formed with a variation in one or more dimensions on which the stochastic metric is dependent; obtaining optical metrology data including a distribution of the intensity related parameter across a zero or higher order of diffraction of radiation scattered from a structure; and using the trained model to infer a value of the stochastic metric from the optical metrology data.

First claim

1 . A method of determining a stochastic metric relating to a structure, the method comprising:
obtaining a trained model, the model having been trained to correlate training optical metrology data to training stochastic metric data, wherein the training optical metrology data comprises a plurality of measurement signals relating to a plurality of angularly resolved distributions of an intensity related parameter across a zero or higher order of diffraction comprised within radiation scattered from a plurality of training structures on a substrate, and the training stochastic metric data comprises stochastic metric values relating to the plurality of training structures, wherein the plurality of training structures have been formed with a variation in one or more dimensions on which the stochastic metric is dependent; obtaining optical metrology data comprising an angularly resolved distribution of the intensity related parameter across a zero or higher order of diffraction comprised within radiation scattered from a structure; and using the trained model to infer a value of the stochastic metric associated with the structure from the optical metrology data.

2 . The method as claimed in claim 1 , wherein each of the measurement signals further comprises spectrally resolved distributions of the intensity related parameter across a zero or higher order of diffraction comprised within radiation scattered from the plurality of training structures on the substrate.

3 . The method as claimed in claim 1 , wherein the parameter is diffraction efficiency.

4 . The method as claimed in claim 1 , wherein the training optical metrology data further comprises nominal informative metrology data relating to one or both of: non-defect measurements and/or simulations; and/or specific defect measurements or simulations.

5 . The method as claimed in claim 1 , wherein the model comprises a machine learning model, neural network or convolutional neural network.

6 . The method as claimed in claim 1 , wherein the variation in one or more dimensions is associated with a variation in one or more process parameters of a lithographic process used in applying the training structures to the training substrate.

7 . The method as claimed in claim 6 , wherein the said training stochastic metric data describes an acceptable space or range of stochastic metric values or related dimensional metric values, and a corresponding acceptable space or range of values of the one or more process parameters.

8 . The method as claimed in claim 6 , wherein the one or more process parameters are dose and/or focus.

9 . The method as claimed in claim 1 , further comprising the initial steps of:
obtaining the training optical metrology data and stochastic metric data; and training the trained model on the training optical metrology data and stochastic metric data.

10 . The method as claimed in claim 9 , comprising:
obtaining high-resolution metrology data; and determining the stochastic metric data from the high-resolution metrology data.

11 . The method as claimed in claim 10 , wherein the high-resolution metrology data is obtained from scanning electron microscope metrology.

12 . The method as claimed in claim 1 , further comprising using the inferred value for the stochastic metric to decide where and/or when to perform further high-resolution metrology.

13 . The method as claimed in claim 1 , wherein the stochastic metric comprises one or more selected from: defect rate or other defect metric, line edge roughness, line width roughness, local critical dimension uniformity, circle edge roughness or edge placement error.

14 . A non-transitory computer-readable medium comprising a computer program therein, the computer program comprising program instructions operable to cause one or more processors to perform at least the method of claim 1 .

15 . (canceled)

16 . A method of determining a stochastic metric relating to a structure, the method comprising:
obtaining a trained machine learning model, the machine learning model having been trained to correlate training optical metrology data to training stochastic metric data, wherein the training optical metrology data comprises a plurality of measurement signals relating to radiation scattered from a plurality of training structures on a substrate and the training stochastic metric data comprises stochastic metric values relating to the plurality of training structures, wherein the plurality of training structures have been formed with a variation in one or more dimensions on which the stochastic metric is dependent; obtaining optical metrology data from a structure; and using the trained machine learning model to infer a value for the stochastic metric associated with the structure from the optical metrology data.

17 . The method of claim 16 , wherein the stochastic metric represents a defect probability or a CD variation at a spatial scale smaller than 1000 times the CD.

18 . The method of claim 16 , wherein the measurement signal is a zero order pupil intensity distribution of radiation after being scattered by the training structure.

19 . A non-transitory computer-readable medium comprising a computer program therein, the computer program comprising program instructions operable to cause one or more processors to perform at least the method of claim 16 .

20 . A method of determining a stochastic metric relating to a lithographic process, the method comprising:
obtaining a trained model, the model having been trained on training inspection image data and training stochastic metric data, wherein the training inspection image data comprises a plurality of inspection images, each relating to reflected radiation having been reflected by a training structure of a plurality of training structures on a training substrate, and the training stochastic metric data comprises stochastic metric values relating to the training structures, wherein the plurality of training structures have been formed with a variation in one or more dimensions or process parameters on which the stochastic metric is dependent; obtaining inspection image data relating to a structure having been exposed in a lithographic process; and using the trained model to infer a value for the stochastic metric associated with the structure from the inspection image data.

21 . A non-transitory computer-readable medium comprising a computer program therein, the computer program comprising program instructions operable to cause one or more processors to perform at least the method of claim 16 .

Assignees

• Asml Netherlands Bv

Inventors

• Batistakis Chrysostomos
• Pisarenco Maxim
• Van Kraaij Markus Gerardus Martinus Maria
• Rutigliani Vito Daniele
• Middlebrooks Scott Anderson
• Verschuren Coen Adrianus
• Geypen Niels

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G03F7/7065

  Defects, e.g. optical inspection of patterned layer for defects · CPC title

• G03F7/70641

  Focus · CPC title

• G03F7/70625

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