Physics-informed neural networks for hybrid modeling of lab-scale batch fermentation for β-carotene production using Saccharomyces cerevisiae

Systems Engineering Approach to Modeling and Analysis of Chronic Obstructive Pulmonary Disease Part II: Extension for Variable Metabolic Rates

Recently, we developed a systems engineering model of the human cardiorespiratory system [Kurian et al. ACS Omega2023, 8 (23), 20524-20535. DOI: 10.1021/acsomega.3c00854] based on existing models of physiological processes and adapted it for chronic obstructive pulmonary disease (COPD)-an inflammatory lung disease with multiple manifestations and one of the leading causes of death in the world. This control engineering-based model is extended here to allow for variable metabolic rates established at different levels of physical activity. This required several changes to the original model: the model of the controller was enhanced to include the feedforward loop that is responsible for cardiorespiratory control under varying metabolic rates (activity level, characterized as metabolic equivalent of the task-Rm-and normalized to one at rest). In addition, a few refinements were made to the cardiorespiratory mechanics, primarily to introduce physiological processes that were not modeled earlier but became important at high metabolic rates. The extended model is verified by analyzing the impact of exercise (Rm > 1) on the cardiorespiratory system of healthy individuals. We further formally justify our previously proposed adaptation of the model for COPD patients through sensitivity analysis and refine the parameter tuning through the use of a parallel tempering stochastic global optimization method. The extended model successfully replicates experimentally observed abnormalities in COPD-the drop in arterial oxygen tension and dynamic hyperinflation under high metabolic rates-without being explicitly trained on any related data. It also supports the prospects of remote patient monitoring in COPD.

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Hybrid modeling, with an appropriate blend of the mechanistic and data-driven framework, is increasingly being adopted in bioprocess modeling, model-based experimental design (digital-twin), identification of critical process parameters, and optimization. However, the development of a hybrid model from experimental data is an inherently complex workflow, involving designed experiments, selection of the data-driven process, identification of model parameters, assessment fitness, and generalization capability. Depending on the complexity of the process system and purpose, each piece of these modules can flexibly be incorporated into the puzzle. However, this extra flexibility can be a cause of concern to trace an "optimal" model structure. In this paper, the development of hybrid models in a common bioprocess system, selection of data-driven components and their mapping to states, choice of parameter identification techniques, and model quality assurance are revisited. The challenges associated with hybrid-model development, and corrective actions have also been reviewed. The review also suggests the lack of data, and code sharing in communal repositories can be a hurdle in the exploration, and expansion of those tools in a bioprocess system.

Machine learning methods for predicting the key metabolic parameters of Halomonas elongata DSM 2581 T

Ectoine is generally produced by the fermentation process of Halomonas elongata DSM 2581 ^T, which is one of the primary industrial ectoine production techniques. To effectively monitor and control the fermentation process, the important parameters require accurate real-time measurement. However, for ectoine fermentation, three critical parameters (cell optical density, glucose, and product concentration) cannot be measured conveniently in real-time due to time variation, strong coupling, and other constraints. As a result, our work effectively created a series of hybrid models to predict the values of these three parameters incorporating both fermentation kinetics and machine learning approaches. Compared with the traditional machine learning models, our models solve the problem of insufficient data which is common in fermentation. In addition, a simple kinetic modeling is only applicable to specific physical conditions, so different physical conditions require refitting the function, which is tedious to operate. However, our models also overcome this limitation. In this work, we compared different hybrid models based on 5 feature engineering methods, 11 machine-learning approaches, and 2 kinetic models. The best models for predicting three key parameters, respectively, are as follows: CORR-Ensemble (R²: 0.983 ± 0.0, RMSE: 0.086 ± 0.0, MAE: 0.07 ± 0.0), SBE-Ensemble (R²: 0.972 ± 0.0, RMSE: 0.127 ± 0.0, MAE: 0.078 ± 0.0), and SBE-Ensemble (R²:0.98 ± 0.0, RMSE: 0.023 ± 0.001, MAE: 0.018 ± 0.001). To verify the universality and stability of constructed models, we have done an experimental verification, and its results showed that our proposed models have excellent performance. KEY POINTS: • Using the kinetic models for producing simulated data • Through different feature engineering methods for dimension reduction • Creating a series of hybrid models to predict the values of three parameters in the fermentation process of Halomonas elongata DSM 2581 ^T.

Physics-informed machine learning methods for biomass gasification modeling by considering monotonic relationships

Machine learning methods have recently shown a broad application prospect in biomass gasification modeling. However, a significant drawback of the machine learning approaches is their poor physical interpretability when relying on limited experimental data. In the present work, a physics-informed neural network method (PINN) is developed to predict biomass gasification products (N₂, H₂, CO, CO₂, and CH₄). PINN simultaneously considers regression, structure, and physical monotonicity constraints in the loss function, providing physically feasible predictions. Specifically, the PINN models have outperformed prediction capability (average test R² 0.91-0.97) compared to five other machine learning methods through 50 times random sample classifications. Furthermore, it is demonstrated that the developed models can maintain correct monotonicity even if the feedstock characteristics or gasification conditions are outside the training data. By using a reliable physical mechanism to guide machine learning, the model can ensure better generalizability and scientific interpretability.