Predicting resist pattern collapse in EUVL using machine learning

Sean D'Silva; Raghunandan Arava; Andreas Erdmann; Thomas Muelders; Hans-Juergen Stock

doi:10.1117/12.2691987

22 November 2023 Predicting resist pattern collapse in EUVL using machine learning

Sean D'Silva, Raghunandan Arava, Andreas Erdmann, Thomas Muelders, Hans-Juergen Stock

Proceedings Volume PC12750, International Conference on Extreme Ultraviolet Lithography 2023; PC127500I (2023) https://doi.org/10.1117/12.2691987
Event: SPIE Photomask Technology + EUV Lithography, 2023, Monterey, California, United States

Abstract

Predicting and simulating resist defects with the help of rigorous nanomechanical/fluid dynamics simulations can be quite tedious and slow, especially for the use cases expected in EUVL. This is mainly because of the complicated meshing and discretization methods required. The finite element method (FEM) solver would need to solve a large system of equations due to the large number of higher order mesh elements making the overall simulations extremely slow. A total simulation time of several hours was observed while simulating a single rough profile for predicting collapse. Predicting resist defects with the help of simulations therefore requires newer strategies due to the overall randomness caused due to the numerous optical and chemical effects. This is where machine learning could help speed up the process.

Conference Presentation

Citation Download Citation

Sean D'Silva, Raghunandan Arava, Andreas Erdmann, Thomas Muelders, and Hans-Juergen Stock "Predicting resist pattern collapse in EUVL using machine learning", Proc. SPIE PC12750, International Conference on Extreme Ultraviolet Lithography 2023, PC127500I (22 November 2023); https://doi.org/10.1117/12.2691987

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