New publication delves into Machine Learning based soft sensors
Real-time predictions in fermentation processes are crucial because they enable continuous monitoring and control of bioprocessing. This research ties into previous work and publication and introduces a proof of concept of a Machine Learning Operations (MLOps) pipeline to automate the end-to-end soft sensor lifecycle in industrial scale fed-batch fermentation.
In this publication, Brett Metcalfe, Juan Camilo Acosta-Pavas, Carlos Eduardo Robles-Rodriguez, George K. Georgakilas, Theodore Dalamagas, Cesar Arturo Aceves-Lara, Fayza Daboussi, Jasper J Koehorst and David Camilo Corrales demonstrate how MLOps can improve the development, deployment, maintenance, and monitoring of ML-based soft sensors, enhancing real-time process control, in line with Bioindustry 4.0’s goal to create and optimise digital shadows and twins for bioprocess design and control.
You can read the full article here: https://www.sciencedirect.com/science/article/abs/pii/S0098135424004095