Latent State Space Extension for interpretable hybrid mechanistic models

Mechanistic growth models play a major role in bioprocess engineering, design, and control. Their reasonable predictive power and their high level of interpretability make them an essential tool for computer aided engineering methods. Additionally, since they contain knowledge about cell physiology, the parameter estimates provide meaningful insights into the metabolism of the microorganism under study. However, the assumption of time invariance of the model parameters is often violated in real experiments, limiting their capacity to fully explain the observed dynamics. In this work, we propose a framework for identifying such violations and producing insights into misspecified mechanisms. The framework achieves this by allowing kinetic and process parameters to vary in time. We demonstrate the framework's capabilities by fitting a hybrid model based on a simple mechanistic growth model for E. coli with data generated in-silico by a much more complex one and identifying missing kinetics.