Deep Learning for Model Calibration in Simulation of Itaconic Acid Production
For bioprocess engineers, this provides a data-efficient framework for parameter estimation in dynamic models, though the improvement is incremental over existing methods.
The study uses deep learning to estimate kinetic parameters for modeling itaconic acid production, comparing direct deep learning (DDL) and generative conditional flow matching (CFM). CFM consistently yields more accurate results, closely matching nonlinear regression, while DDL shows larger deviations, demonstrating CFM's reliability across scales.
In this study, deep learning is used to estimate kinetic parameters for modeling itaconic acid production based on real batch experiments conducted at different agitation speeds and reactor scales. Two deep learning strategies, namely direct deep learning (DDL) and generative conditional flow matching (CFM) are compared and benchmarked against nonlinear regression as a reference method. Compared with DDL, CFM consistently yields more accurate results. The concentration profiles predicted by CFM closely match those obtained from nonlinear regression, whereas DDL results in larger deviations. Similar behavior is observed in the scale-up experiments, where the CFM model again generalizes better and is more robust than the direct approach. These findings demonstrate that CFM can reliably predict system behavior across different operating conditions and scales, offering a flexible and data-efficient framework for parameter estimation in dynamic bioprocess models.