Making waves: Transforming biofilm-based wastewater treatment using machine learning-driven real-time monitoring
Oliver J. Fisher, Yanming Wang, Asma Ahmed
Abstract
Biofilm-mediated processes hold significant promise for sustainable and effective wastewater treatment. However, their widespread adoption remains constrained by the complexity of biofilm dynamics and the lack of effective real-time monitoring tools. Existing approaches often rely on indirect measurements or disruptive sampling, offering limited insight into the dynamic nature of these systems. This "Making Waves" article explores a pivotal question: Can real-time monitoring solutions unlock the full potential of biofilm-mediated wastewater treatment? We propose that integrating artificial intelligence (AI) and machine learning (ML) with non-invasive sensors offers a transformative solution. By training ML models on continuous sensor data, key biofilm properties like thickness, density, and structural dynamics can be inferred in real time, enabling more interpretable and biologically informed process control. This approach moves beyond static measurements and opaque "black-box" models, offering transparent, predictive insights into biofilm behaviour. Ultimately, AI-enabled monitoring systems can support adaptive control, enhance operational stability, and improve treatment efficiency. By making biofilm dynamics visible and actionable, this strategy lays the foundation for more intelligent, responsive, and resilient wastewater treatment systems.