Pairing wafer leveling metrology from a lithographic apparatus with deep learning to enable cost effective dense wafer alignment metrology

Schmitt-Weaver, Emil; Bhattacharyya, Kaustuve

doi:10.1117/12.2514455

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML and deep learning (DL) architectures and techniques have been applied in various tasks in the production line including overlay metrology, [3][4][5] wafer leveling and alignment, 6 defect detection and classification, 7,8 SEM images denoising, 9 and mask optimization, [10][11][12][13] and they have shown great improvement compared to conventional algorithms both in terms of accuracy and speed. In this research, we have demonstrated the application of our deep learning denoiser assisted framework towards enabling SEM contour extraction possible for all the edges in raw noisy DRAM SEM images with bit-line-periphery (BLP) and storage node landing pad (SNLP) patterns.…”

Section: Introductionmentioning

confidence: 99%

A deep learning facilitated approach for SEM image denoising towards improved contour extraction for 1D and 2D structures

Dey,

Wu,

Blanco

et al. 2023

38th European Mask and Lithography Conference (EMLC 2023)

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

A deep learning facilitated approach for SEM image denoising towards improved contour extraction for 1D and 2D structures

Dey,

Wu,

Blanco

et al. 2023

38th European Mask and Lithography Conference (EMLC 2023)

View full text Add to dashboard Cite

“…The thriving of ML has also quickly expanded to the semiconductor industry. ML and deep learning (DL) architectures and techniques have been applied in various tasks in the production line including overlay metrology [4]- [6], wafer leveling and alignment [7], defect detect and classification [8], [9], SEM images denoising [10], and mask optimization [11]- [15], and they have shown great improvement compared to conventional algorithms both in terms of accuracy and speed. Utilizing the advancement of ML techniques, we have proposed two methods to denoise SEM images for better analysis after measurement.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning based SEM image Denoising Approaches for Improving Metrology and Inspection of Thin Resists

Dey¹

2023

Preprint

View full text Add to dashboard Cite

<p>As semiconductor manufacturing is moving towards 3 nm nodes and beyond, the development of advanced metrology techniques to control the quality of fabricated features on silicon wafers is becoming more and more crucial. Among the popular metrology methods, Scanning Electron Microscopy is one of the most important techniques since it can produce images with resolutions as low as a few nanometers. Thus, SEM is very suitable to inspect the critical dimension of nanoscale printed structures. However, CD-SEM images intrinsically contain a significant amount of background noise due to various sources. This background noise can lead to inaccurate metrology and erroneous defect detection. There is a significant requisite to reduce the noise signal in CD-SEM images while keeping the actual morphology of the pattern feature unaltered. In this paper, we proposed two deep learning-based methods to denoise SEM images, one based on (1) supervised/semi-supervised learning technique, and the other based on (2) unsupervised learning. The two proposed methods were experimented with different noisy SEM images of categorically different geometrical patterns and have demonstrated exceptional performance in reducing noise both qualitatively and quantitatively. We also have demonstrated how our proposed deep learning denoiser is applicable towards challenging application scenarios such as defect inspection and contour extraction, specifically with thin resists, with significantly improved accuracy. First, we have validated that our proposed denoising techniques, especially the unsupervised model, are effective. The unsupervised training scheme also requires single noisy acquisitions to train denoising CNNs without any ground-truth or synthetic images, against previous supervised/semi-supervised data greedy approaches. Second, the proposed deep learning denoiser assisted framework allows improved defect inspection and contour extraction with thin resists. The goal of this work is to establish a robust de-noising technique to reduce the dependency of SEM image acquisition settings and to extract repeatable and accurate CDSEM metrology information for high NA EUV. Finally, the limitations of our proposed approaches and how to overcome them were also thoroughly discussed. </p>

show abstract

Machine Learning-Based Edge Placement Error Analysis and Optimization: A Systematic Review

Ngo

Dey

Halder

et al. 2023

IEEE Trans. Semicond. Manufact.

View full text Add to dashboard Cite

Pairing wafer leveling metrology from a lithographic apparatus with deep learning to enable cost effective dense wafer alignment metrology

Cited by 3 publications

References 5 publications

A deep learning facilitated approach for SEM image denoising towards improved contour extraction for 1D and 2D structures

A deep learning facilitated approach for SEM image denoising towards improved contour extraction for 1D and 2D structures

Deep Learning based SEM image Denoising Approaches for Improving Metrology and Inspection of Thin Resists

Machine Learning-Based Edge Placement Error Analysis and Optimization: A Systematic Review

Contact Info

Product

Resources

About