Virtual metrology: How to bridge between the different data sources
In today’s internet of things economy, the number of semiconductor designs is increasing rapidly. The semiconductor industry needs a more cost-effective way to set up new designs for manufacturing. All available data sources need to be utilized to do the setup. In this paper we suggest two new approaches using big data and machine learning for reusing historical data for future designs: Combining historical fab-generated data with full reticle design features to predict optimal process conditions, and the concept of cross-metrology integration of fab-generated data across multiple metrology steps to improve data quality.
A version of this paper was presented by Siemens and GLOBALFOUNDRIES authors at SPIE Advanced Lithography + Patterning in 2022 and published in the proceedings, volume 12053.