Synergistic integration of microbial fuel cells with artificial intelligence and machine learning: Towards sustainable and self-optimizing bioelectrochemical system

Bioelectrochemical systems (BESs) present a compelling avenue for sustainable energy generation and the remediation of wastewater. Nevertheless, the intricate interplay of their biological and electrochemical processes presents considerable obstacles for conventional modelling methodologies. Microbial Fuel Cells (MFCs), a notable area of sustainable technology, facilitate concurrent wastewater treatment and bioenergy retrieval. However, their widespread practical implementation is currently constrained by low power output, nonlinear electrochemical kinetics, and susceptibility to environmental variability. This review investigates the latest advancements in the use of artificial intelligence (AI) techniques to enhance the effectiveness and expandability of BES technologies. We outline the contributions of machine learning (ML) algorithms, comprising artificial neural networks (ANNs), support vector regression (SVR), and random forest (RF) in predicting key BES performance indicators. Emphasis is placed on the incorporation of AI-driven real-time monitoring and adaptive control systems in response to changing environmental conditions of BESs. Notwithstanding these significant breakthroughs, ongoing difficulties persist, especially with regards to data standardization and the precise modelling of biological intricacies within BES. We proposed recent setbacks and potential research paths, emphasizing the need for complete data sets, uniform procedures, and advanced AI systems to fully utilize the capabilities of AI-boosted BES systems in achieving environmentally sustainable bioenergy objectives. AI models have shown that they can effectively explain the complex relationships between operating factors like pH, temperature, and substrate concentration, and voltage production, which has resulted in notable prediction accuracy.