A few-shot machine learning-based OCD metrology algorithm with anomaly detection and wafer-level data augmentation

Minkyu Kim; QHwan Kim; Kyu-Baik Chang; Jaehoon Jeong; Sunghee Lee; Seonghui Mo; Dahan Kang; Jinkook Park; Young-Seok Kim; Yongdeok Jeong; Dae Sin Kim

doi:10.1117/12.3009965

9 April 2024 A few-shot machine learning-based OCD metrology algorithm with anomaly detection and wafer-level data augmentation

Minkyu Kim, QHwan Kim, Kyu-Baik Chang, Jaehoon Jeong, Sunghee Lee, Seonghui Mo, Dahan Kang, Jinkook Park, Young-Seok Kim, Yongdeok Jeong, Dae Sin Kim

Author Affiliations +

Proceedings Volume 12955, Metrology, Inspection, and Process Control XXXVIII; 129550U (2024) https://doi.org/10.1117/12.3009965
Event: SPIE Advanced Lithography + Patterning, 2024, San Jose, California, United States

Abstract

With the increasing complexity of 3-D semiconductor structures, the use of optical critical dimension (OCD) metrology has become a popular solution due to its accuracy and fast inference time. Machine learning has been widely adopted in this field to further improve the efficiency and precision of OCD metrology. Especially for high aspect ratio structures such as DRAM and VNAND, where the required computing power for physical modeling increases exponentially, the importance of machine learning with reference data is crucial. However, one significant challenge of the machine learning-based metrology under rapidly changing process condition is the limitation of available labeled data, which causes overfitting and decreases recipe reliability in the manufacturing process as the cost of wafer consumption increases. To utilize machine learning algorithms in mass production, the development of robust algorithms that can be optimized with few-shot data is required. In this paper, we propose a few-shot machine learning algorithm that includes i) wafer-level statistical information-based data augmentation and ii) anomaly detection to automatically remove data with measurement errors. The proposed algorithm shows superior accuracy, repeatability, and in-wafer uniformity compared to the benchmark algorithm in tests with manufacturing phase data. Additionally, this robustness can be sustained with the minimum amount of data in metrology, as only 9 reference training data are used on three design of experiment (DoE) wafers. The proposed optimized solution is expected to contribute to the reduction of measurement costs and production yields of highly complicated 3D semiconductor structures.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Minkyu Kim, QHwan Kim, Kyu-Baik Chang, Jaehoon Jeong, Sunghee Lee, Seonghui Mo, Dahan Kang, Jinkook Park, Young-Seok Kim, Yongdeok Jeong, and Dae Sin Kim "A few-shot machine learning-based OCD metrology algorithm with anomaly detection and wafer-level data augmentation", Proc. SPIE 12955, Metrology, Inspection, and Process Control XXXVIII, 129550U (9 April 2024); https://doi.org/10.1117/12.3009965

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available