Master Thesis: Development & Evaluation of ML Models for Catalysts in Exhaust Aftertreatment Systems

This master thesis focuses on developing and evaluating machine learning models for catalysts in exhaust aftertreatment systems, exploring the boundary between physical modeling and machine learning. The role involves systematically evaluating compact ML architectures for dynamic modeling of catalysts, assessing their performance, and supporting the development of guidelines for ML-based catalyst models. The project also explores combining physical models, machine learning, and automated modeling pipelines to manage information across multiple scales.