My research focuses on developing predictive digital models for bioprocesses.
These are manufacturing processes that use living organisms such as bacteria or fungi to produce valuable compounds. Many critical biological states in fermentation cannot be measured in real time, yet controlling them is essential for efficient, sustainable production. The aim is to build virtual sensors and predictive models that support improved process operation and decision making.
The project combines mechanistic bioprocess modelling with machine learning based methods, using historical and real time data from fermentations, including process sensors, off gas analysis, and spectroscopic measurements.
Inefficient bioprocesses carry both economic and environmental costs. By enabling tighter control and deeper understanding of fermentation, this research contributes to more sustainable production of the industrial enzymes and proteins that underpin modern food processing and bio-based manufacturing.
