Machine Learning Models for Edge Placement Error Based Etch Bias

Meng, Yunxiao; Kim, Young-Chang; Guo, Shujie; Shu, Zhongli; Zhang, Yingchun; Liu, Qingwei

doi:10.1109/tsm.2020.3042803

Cited by 9 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further author information: (Send correspondence to Sooyong Lee) *Jeeyong Lee: jeeyong.lee@samsung.com, †Sooyong Lee: sooyong.lee@samsung.com As described above, the classical PPC has revealed a limitation in that it is difficult to properly model the correlation between the design layout and the etch process. Thus, recently there have been attempts to supplement the method through the use of artificial intelligence (AI) technology [6][7][8][9][10]. As rasterized image based AI approaches often cannot ensure their shift invariance, and their results depend on the grid size of their pixel [11,12], they might even worsen the present problem.…”

Section: Introductionmentioning

confidence: 99%

A novel approach to etch-process-aware intensive layout retarget

Lee

Heo

Lee

et al. 2023

Advanced Etch Technology and Process Integration for Nanopatterning XII

View full text Add to dashboard Cite

Patterning, a major process in semiconductor manufacturing, aims to transfer the design layout to the wafer. Accordingly, the "process proximity correction" method was developed to overcome the difference in after-cleaninginspected CD (critical dimension) between patterns of similar shapes. However, its physical model is often limited in the predictive performance. Therefore, recent studies have introduced ML (machine learning) technology to supplement model accuracy, but this approach often has an inherent risk of overfitting depending on the type of sampled pattern. In this study, we present a newly invented flow capable of stable etch-process-aware ML modeling by model reconstruction and large amounts of measurement data. The new modeling flow can also be performed within a reasonable runtime through efficient feature extraction. Based on the new model and its related layout targeting platform, intensive improvements were made to CD targeting and spread; for a given layout, in comparison with delicate rule-based modification, the CD targeting accuracy was improved by 4 times and approaches the limit of metrology error.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel approach to etch-process-aware intensive layout retarget

Lee

Heo

Lee

et al. 2023

Advanced Etch Technology and Process Integration for Nanopatterning XII

View full text Add to dashboard Cite

show abstract

“…To reduce the error in the printing, the earliest corrections in mask design could be tracked back to 1981. 6) Recently, deep learning (neural networks) has been used in the field of optical lithography for optical correction, [7][8][9][10][11][12] hotspot correction, [13][14][15][16][17][18][19] etching bias correction, 11,[20][21][22] and simulation model construction. 23) The neural networks were not only used for prediction and defect correction but also implemented in image classification.…”

Section: Introductionmentioning

confidence: 99%

Classification of lines, spaces, and edges of resist patterns in scanning electron microscopy images using unsupervised machine learning

Jin

Kozawa

2022

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

As key steps of lithography, the development of resist materials and the exploration of new materials are important to meet market demands from semiconductor industry. During the development, resist materials are usually evaluated by the information extracted from their scanning electron microscopy (SEM) images. The information extracted from SEM images is not always accurate owing to the technical limitation. Accurate information extraction is also useful for the prediction of an etched substrate pattern. In this paper, we reported a strategy to classify the image pixels of line-and-space resist patterns into line, space, and edge classes, using unsupervised machine learning. Brightness and coordination information was integrated into the classification method. The high reliability in classification was demonstrated by hierarchical clustering based on its information integrating ability. Among all the methods of hierarchical clustering examined, the centroid method was the most accurate strategy for extracting information from a single SEM image.

show abstract