Modeling ECD With Machine Learning to Improve CMP Simulation

White Paper Overview

Accurate modeling of post-ECD surface topography variation is crucial for correct CMP simulation. Siemens and the American University of Armenia collaborated to investigate and evaluate the use of machine learning (ML) modeling techniques to predict these complicated topography variations.

Using various ML methods to model post-ECD surface profiles and comparing the results enabled them to determine which architectures and models provided the best combination of running time and accuracy.

This white paper investigates the use of advanced machine learning (ML) modeling techniques to predict complicated topography variations. It also provides a demonstration of the application of various ML methods to model surface profiles after ECD. The resource showcases results that determine which architectures and models provide the best combination of running time and accuracy.