Abstract
Sustainable development goals have spurred advancements in bioprocess design, driven by improved process monitoring, data storage, and computational power. High-fidelity models are essential for advanced process system engineering, yet accurate parametric models for bioprocessing remain challenging due to overparameterization, often resulting in poor predictive accuracy. Hybrid modeling, combining parametric and non-parametric methods, offers a promising solution by enhancing accuracy while maintaining interpretability. This study explores hybrid models for succinic acid fermentation by Escherichia coli, a critical process for sustainable bio-based chemical production. The research presents a structured exploration of hybrid model architectures and their robustness under varying conditions. Experimental data were preprocessed to remove noise and outliers, and hybrid model structures were developed with differing levels of hybridization (from one to all reaction rates). Kinetic parameters were recalibrated and compared against original values. Machine learning algorithms, including Artificial Neural Networks, Support Vector Machines, and Gaussian Processes, were tested, with tuning strategies applied to original or recalibrated parameters. Due to a considerable variability in individual model performance for validation, an ensemble learning approach was proposed to enhance robustness. Results demonstrate that despite not solving the overparametrization issues, all hybrid models outperform the original parametric model, with the best-performing hybrid model achieving a 52.3% lower RMSE of validation, avoiding overfitting. Ensemble approaches further improved predictions, reducing RMSE by up to 62.3% compared to individual parametric models. This highlights hybrid modeling’s potential to enhance bioprocess prediction accuracy, even with limited data, supporting future advancements in bioprocess scale-up, digitalization, and sustainable biorefinery implementations.