Machine learning based recursive partitioning for simplifying OPC model building complexity

Apoorva Oak, Soobin Hwang, Ruoxia Chen, Shinill Kang, Ryan Ryoung Han Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We propose the use of machine learning based analytics to simplify OPC (Optical Proximity Correction) model building process which demands concurrent optimization of more than 70 parameters as nodes shrink. We first built a deep neural network architecture to predict the RMS error, for a given set of model parameters. The neural network was trained on existing OPC model parameters and corresponding output RMS data of simulations to achieve an accurate prediction of output RMS for given set of OPC model parameters. Later, a sensitivity analysis-based methodology for recursive partitioning of OPC modelling parameters was employed to reduce the total search space of OPC model simulations. This resulted in reduction of the number of OPC model iterations performed during model tuning by orders of magnitude.

Original languageEnglish
Title of host publicationDesign-Process-Technology Co-optimization XV
EditorsChi-Min Yuan, Ryoung-Han Kim
ISBN (Electronic)9781510640610
Publication statusPublished - 2021
EventDesign-Process-Technology Co-optimization XV 2021 - Virtual, Online, United States
Duration: 2021 Feb 222021 Feb 26

Publication series

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


ConferenceDesign-Process-Technology Co-optimization XV 2021
Country/TerritoryUnited States
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021 SPIE.

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Machine learning based recursive partitioning for simplifying OPC model building complexity'. Together they form a unique fingerprint.

Cite this