ABSTRACT
The use of machine learning has been well documented in recent years in a wide variety of optical scatterometry applications. Machine learning can either be used in a ‘modeless’ manner to directly correlate measured spectra to reference metrology without an optical model or serve as a complementary technique together with conventional scatterometry modeling to improve the sensitivity of specific parameters.
This work presents both modeless and AI augmented scatterometry modeling applications in the gate-all-around nanosheet process flow. AI augmented scatterometry models were generated for measurements at adjacent
patterning steps and were validated by conventional TEM correlation. A concept is introduced to utilize modeless machine learning solutions as a complementary technique with AI segmented scatterometry models at consecutive
process steps. The forward and backward prediction of selected measurement steps is studied to identify possible inconsistencies between the outputs of the associated scatterometry models.
An intercorrelation matrix is assembled to tabulate average correlation of 6 modeless machine learning models to the corresponding previous / future step scatterometry model output. This bidirectional machine learning
assessment proves to be a simple methodology to reveal the intercorrelation between past and future process steps and helps to identify both model and process stabilities.
Keywords: Machine Learning, scatterometry, modeless, AI augmented scatterometry, reference metrology, bidirectional intercorrelation, replacement metal gate
*Corresponding author: [email protected]