Enhancing process monitoring and control in novel carbon capture and utilization biotechnology through artificial intelligence modeling: An advanced approach toward sustainable and carbon-neutral wastewater treatment

Abstract

Integrating carbon capture and utilization (CCU) technologies into wastewater treatment plants (WWTPs) is essential for mitigating greenhouse gas (GHG) emissions and enhancing environmental sustainability, but further advancements in process monitoring and control are critical to optimizing treatment performance. This study investigates the application of artificial intelligence (AI) modeling to enhance process monitoring and control in a novel integrated CCU biotechnology with a moving bed biofilm reactor (MBBR) sequenced with an algal photobioreactor (aPBR). This system reduces GHG and odour emissions simultaneously. Several machine learning (ML) models, including artificial neural networks (ANNs), support vector machines (SVM), random forest (RF), and least-squares boosting (LSBoost), were tested. The LSBoost was the most suitable for modeling the MBBR + aPBR system, exhibiting the highest accuracy in predicting CO₂ (R² = 0.97) and H₂S (R² = 0.95) emissions from the MBBR. LSBoost also achieved the highest accuracy for predicting CO₂ (R² = 0.85) and H₂S (R² = 0.97) outlet concentrations from the aPBR. These findings underscore the importance of aligning AI algorithms to the characteristics of the treatment technology. The proposed AI models outperformed conventional statistical methods, demonstrating their ability to capture the complex, nonlinear dynamics typical of processes in environmental technologies. This study highlights the potential of AI-driven monitoring and control systems to significantly improve the efficiency of CCU biotechnologies in WWTPs for climate change mitigation and sustainable wastewater management.