Deep Learning for Model Calibration in Simulation of Itaconic Acid Production

TL;DR

This paper compares deep learning methods for estimating parameters in itaconic acid production models, finding that generative conditional flow matching (CFM) outperforms direct deep learning and nonlinear regression.

Contribution

It introduces and benchmarks CFM as a robust, data-efficient deep learning approach for dynamic bioprocess parameter estimation across scales.

Findings

CFM yields more accurate parameter estimates than DDL.

CFM closely matches nonlinear regression in concentration profile predictions.

CFM generalizes better and is more robust in scale-up experiments.

Abstract

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.