Asml Netherlands B.v.

Jing Su

Yen-Wen Lu

Yi Zou

Ya Luo

Stefan Hunsche

Youping Zhang

Marinus Jochemsen

Rafael C Howell

Been-Der Chen

Lin Lee Cheong

Chenxi Lin

Quan Zhang

Maxime Philippe Frederic Genin

Weixuan Hu

Cong Wu

Yu Long Cao

Duan-Fu Stephen Hsu

Christopher A Spence

Robert John Socha

Jun Tao

Stanislas Hugo Louis Baron

Training methods and a mask correction method. One of the methods is for training a machine learning model configured to predict a post optical proximity correction (OPC) image for a mask. The method involves obtaining (i) a pre-OPC image associated with a design layout to be printed on a substrate, (ii) an image of one or more assist features for the mask associated with the design layout, and (iii) a reference post-OPC image of the design layout; and training the machine learning model using the pre-OPC image and the image of the one or more assist features as input such that a difference between the reference image and a predicted post-OPC image of the machine learning model is reduced.

Method for training machine learning model to determine optical proximity correction for mask

Methods of identifying a hot spot from a design layout or of predicting whether a pattern in a design layout is defective, using a machine learning model. An example method disclosed herein includes obtaining sets of one or more characteristics of performance of hot spots, respectively, under a plurality of process conditions, respectively, in a device manufacturing process; determining, for each of the process conditions, for each of the hot spots, based on the one or more characteristics under that process condition, whether that hot spot is defective; obtaining a characteristic of each of the process conditions; obtaining a characteristic of each of the hot spots; and training a machine learning model using a training set including the characteristic of one of the process conditions, the characteristic of one of the hot spots, and whether that hot spot is defective under that process condition.

Identification of hot spots or defects by machine learning

A method including: obtaining data based an optical proximity correction for a spatially shifted version of a training design pattern; and training a machine learning model configured to predict optical proximity corrections for design patterns using data regarding the training design pattern and the data based on the optical proximity correction for the spatially shifted version of the training design pattern.

Training methods for machine learning assisted optical proximity error

Methods for training a process model and determining ranking of simulated patterns (e.g., corresponding to hot spots). A method involves obtaining a training data set including: (i) a simulated pattern associated with a mask pattern to be printed on a substrate, (ii) inspection data of a printed pattern imaged on the substrate using the mask pattern, and (iii) measured values of a parameter of the patterning process applied during imaging of the mask pattern on the substrate; and training a machine learning model for the patterning process based on the training data set to predict a difference in a characteristic of the simulated pattern and the printed pattern. The trained machine learning model can be used for determining a ranking of hot spots. In another method a model is trained based on measurement data to predict ranking of the hot spots.

Determining pattern ranking based on measurement feedback from printed substrate

Training methods for machine learning assisted optical proximity error correction

A method to determine a curvilinear pattern of a patterning device that includes obtaining (i) an initial image of the patterning device corresponding to a target pattern to be printed on a substrate subjected to a patterning process, and (ii) a process model configured to predict a pattern on the substrate from the initial image, generating, by a hardware computer system, an enhanced image from the initial image, generating, by the hardware computer system, a level set image using the enhanced image, and iteratively determining, by the hardware computer system, a curvilinear pattern for the patterning device based on the level set image, the process model, and a cost function, where the cost function (e.g., EPE) determines a difference between a predicted pattern and the target pattern, where the difference is iteratively reduced.

Method for determining curvilinear patterns for patterning device

A method includes obtaining a sub-layout having an area that is a performance limiting spot, adjusting colors of patterns in the area, and determining whether the area is still a performance limiting spot. Another method includes decomposing patterns in a design layout into multiple sub-layouts; determining for at least one area in one of the sub-layouts, the likelihood of that a figure of merit is beyond its allowed range; and if the likelihood is above a threshold, that one sub-layout has a performance limiting spot. Another method includes: obtaining a design layout having a first group of patterns and a second group of patterns, wherein colors of the first group of patterns are not allowed to change and colors of the second group of patterns are allowed to change; and co-optimizing at least the first group of patterns, the second group of patterns and an illumination of a lithographic apparatus.

Coloring aware optimization

Growing community of inventors

Fremont, CA, United States of America

Jing Su