Leveraging artificial intelligence to detect sensor issues and operational problems in sewer systems

This presentation is a case study on the use of artificial intelligence (AI) to detect issues and operational problems in sewer systems more quickly and reliably by identifying anomalies in sewer flow data, including: -Sudden shifts indicative of issues such as sensor failure or blockages in the system -More gradual changes in the data over longer periods of time, which point to issues like sensor drift or other less immediately obvious operational or environmental problems -Differences between calibrated hydraulic models and sensor data The authors will discuss the application of our AI based approach for detecting anomalies in a large water/wastewater agency located in the midwestern united states. We have found that our AI based approach is highly effective at detecting subtle anomalies such as sensor drift, as well as sudden shifts in the flow data. In some instances, it has detected issues weeks before they would have otherwise been detected during manual review or inspection. Not only is the solution effective, but we also chose an approach that is relatively easy to understand and explain, which makes it more actionable and less challenging to maintain. Through our presentation, the authors intend to highlight the critical role that engineering subject matter expertise played in the formulation of our successful approach, and demonstrate the success that can be achieved through the nexus of data science and engineering.