Predicting the critical features of the chemically-amplified resist profile based on machine learning

Pengjie Kong, Lisong Dong*, Xu Ma, Yayi Wei

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The improvement of accuracy and efficiency in simulating the profile of the chemically amplified resist (CAR) is always a key point in lithography. With the development of machine learning, many models have been successfully applied in optical proximity correction (OPC), hotspot detection, and other lithographic fields. In this work, we developed a neural network for predicting the critical features' sizes of the CAR profile. By using a pre-calibrated physical resist model, the effectiveness of this model is demonstrated from numerical simulation. The results indicate that for the critical dimensions (CDs) of the CAR profile, this model shows great speed and accuracy. After applying the tuned neural network on the test sets, it shows 92.98% of the test sets have a mean square error (MSE) less than 1%.

Original languageEnglish
Title of host publicationAdvances in Patterning Materials and Processes XL
EditorsDouglas Guerrero, Gilles R. Amblard
PublisherSPIE
ISBN (Electronic)9781510661035
DOIs
Publication statusPublished - 2023
EventAdvances in Patterning Materials and Processes XL 2023 - San Jose, United States
Duration: 27 Feb 20231 Mar 2023

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12498
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceAdvances in Patterning Materials and Processes XL 2023
Country/TerritoryUnited States
CitySan Jose
Period27/02/231/03/23

Keywords

  • chemically amplified resist
  • critical feature
  • machine learning
  • neural network.
  • predict

Fingerprint

Dive into the research topics of 'Predicting the critical features of the chemically-amplified resist profile based on machine learning'. Together they form a unique fingerprint.

Cite this