Novel ellipsometry-based machine learning technique for characterization of low sensitivity critical dimensions within gate-all-around transistors

We propose a versatile ellipsometry methodology that overcomes poor sensitivity and increases accuracy through a novel principal component approximation (PCA) method of the ML training algorithm with RCWA assistance. Furthermore, our methodology introduces a new ML training concept based on reference data statistics, rather than raw reference. The approach has been successfully employed to monitor sheet-specific indent within GAA architectures and was validated with reference data from cross-sectional transmission electron microscopy images. The proposed methodology paves the way to measuring low sensitivity CDs with highly accurate, noise-reduced and robust ML based physical OCD models for any logic and memory application.