Hybrid machine-learning for dynamic plant-wide biomanufacturing

This study focuses on biomanufacturing case study, i.e. Lovastatin production, employing a hybrid modeling framework that combines mechanistic and data-driven approaches. A time-series da-taset was generated using the KT-Biologics I (KTB1) plantwide model, a dynamic simulation of continuous biomanufacturing. The dataset captures critical parameters such as nutrient concen-trations and API production. The AI-DARWIN framework was used to develop interpretable ma-chine learning models with constrained functional forms, ensuring both accuracy and clarity. The resulting polynomial-based models reveal key relationships between process variables and sys-tem performance, bridging mechanistic insights with data-driven predictions. The models demon-strated reasonable accuracy showing minimal difference between the training and testing errors, highlighting their strong generalization. This work advances hybrid modeling in biomanufacturing by integrating plant-wide mechanistic simulations with interpretable machine learning. The ap-proach ensures both accuracy and transparency while enabling robust process monitoring and control at a ‘plant-wide’ level, contributing to the broader adoption of hybrid modeling in bioman-ufacturing.