Some of our latest research has been published in Computers and Chemical Engineering under the title "Soft sensors based on interpretable learners for industrial-scale fed-batch fermentation: Learning from simulations". This study explores the use of interpretable models like CART, M5, CUBIST, and Random Forest as soft sensors to predict penicillin concentration during industrial-scale fermentation.

Juan Camilo Acosta Pavas, Carlos E Robles Rodriguez, David Griol Barres, Fayza Daboussi, Cesar Arturo Aceves-Lara highlight how these advanced data-driven approaches, a cornerstone of Bioindustry 4.0, can significantly enhance process monitoring and control in the biopharmaceutical industry. Integration of these smart sensors will help to achieve consistent, high-quality production, aligning with the goals of process automation and Industry 4.0.

You can read the full article here: https://www.sciencedirect.com/science/article/abs/pii/S0098135424001546