Modeling of Continuous PHA Production by a Hybrid Approach Based on First Principles and Machine Learning

Abstract

Polyhydroxyalkanoates (PHA) are renewable alternatives to traditional oil-derived polymers. PHA can be produced by different microorganisms in continuous culture under specific media composition, which makes the production process both promising and challenging. In order to achieve large productivities while maintaining high yield and efficiency, the continuous culture needs to be operated in the so-called dual nutrient limitation condition, where both the nitrogen and carbon sources are kept at very low concentrations. Mathematical models can greatly assist both design and operation of the bioprocess, but are challenged by the complexity of the system, in particular by the dual nutrient-limited growth phenomenon, where the cells undergo a metabolic shift that abruptly changes their behavior. Traditional, non-structured mechanistic models based on Monod uptake kinetics can be used to describe the bioreactor operation under specific process conditions. However, in the absence of a model description of the metabolic phenomena inside the cell, the extrapolation to a broader operation domain (e.g., different feeding concentrations and dilution rates) may present mismatches between the predictions and the actual process outcomes. Such detailed models may require almost perfect knowledge of the cell metabolism and omic-level measurements, hampering their development. On the other hand, purely data-driven models that learn correlations from experimental data do not require any prior knowledge of the process and are therefore unbiased and flexible. However, many more data are required for their development and their extrapolation ability is limited to conditions that are similar to the ones used for training. An attractive alternative is the combination of the extrapolation power of first principles knowledge with the flexibility of machine learning methods. This approach results in a hybrid model for the growth and uptake rates that can be used to predict the dynamic operation of the bioreactor. Here we develop a hybrid model to describe the continuous production of PHA by Pseudomonas putida GPo1 culture. After training, the model with experimental data gained under different dilution rates and medium compositions, we demonstrate how the model can describe the process in a wide range of operating conditions, including both single and dual nutrient-limited growth.

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

“…Production of Poly-β-hydroxybutyrate (PHB) by Ralstonia Eutropha has been addressed by Patnaik et al ( 2008) [41] . The authors demonstrated the superiority of the hybrid model Putida GPo1 [42] . The hybrid model was shown to describe the process in a wide range of operating conditions, including single and dual nutrient-limited growth conditions.…”

Towards a Sustainable Circular Economy: Algae‐Based Bioplastics and the Role of Internet‐of‐Things and Machine Learning

“…The study of Saboe et al [134] effectively correlated microbial photoelectrosynthesis (MPS) signals with high algae concentrations in an algal cultivation pond, demonstrating the viability of using AI/ML in the monitoring and controlling microalgae cultivation processes via strong linear correlations and low normalized root mean square error (NRMSE) values. Through the integration of ML with real-time monitoring systems, potential disturbances in microalgae cultivation can be identified and corrected promptly, ensuring a steady and highquality bioplastic production [135].…”

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

“…First, multiple experimental data sets are simultaneously fitted to the mechanistic model. In a refitting exercise, the parameters related to growth, uptake, and product formation rates are independently estimated for each data set while leaving other parameters at their global estimates (Luna et al, 2021). The simulated states can be used to calculate the specific rates using the model equations, and this compilation can subsequently be used to train the data-driven components of the hybrid model.…”

“…The constraints imposed by conservation equations ensure the robustness (Tsopanoglou & Jiménez del Val, 2021), and prediction accuracy of hybrid models in an identified valid domain (Bae et al, 2020). Automated identification of data‐driven architecture reduces the expertise required for the parametric representation of the mechanistic part (Lopes Dias et al, 2007; Luna et al, 2021). Increased process knowledge from hybrid modeling when combined with the design of experiments (DoE), can reduce the experimental burden and accelerate process development (Bayer et al, 2020b).…”