Our current research focuses on the management of big data generated by wastewater treatment plants, leveraging artificial intelligence to enhance operational efficiency. We utilize deep learning techniques to predict pipe failures and integrate these predictions into an expert system designed to develop optimal management strategies for water transmission mains across multi-regional water supply networks.
We have also developed a real-time aeration control system that employs machine learning, pattern recognition, statistical analysis, and empirical relationships—achieving energy savings of 30–50% in aeration processes. Another key area of investigation involves phosphorus removal from urban and agricultural runoff using tire-derived aggregate (TDA). Our studies show that shredded tires are effective at removing toxic organic compounds and heavy metals.
Building on this concept, we have explored the use of shredded tires in landfill leachate collection systems and as buffer zones on golf courses to mitigate pesticide runoff. Additionally, we are systematically determining optimal operating conditions for maximizing biological phosphorus removal in high-phosphorus industrial wastewater, such as dairy effluent.
Our past research has included the biological treatment of environmental toxins, waste treatment process development, investigations into the mechanisms of biological phosphorus removal, creation of novel media for toxic compound removal, river restoration, river water quality modeling, and the beneficial reuse of waste materials.