Using Machine Learning to Predict Condition of Sewer Pipes

Wastewater utilities are aiming to implement asset management strategies to minimize costly emergency repairs, to justify expenditures, and to optimize future renewal actions. Failure of wastewater infrastructure systems can cause major social, environmental, and economic impacts. To avoid such problems, several researchers attempted to develop infrastructure condition assessment methodologies to maintain sewer pipe networks at desired condition. Closed-circuit television (CCTV) inspections and assessing the condition of sewer pipes are expensive and hence limited to portions of a sewer network. The data mining approach presented in recent studies is shown capable of unlocking information contained within inspection records and enhances existing pipe inspection practices currently used in the wastewater industry. The predictive capabilities of machine learning model, namely, K-nearest neighbors (KNN) is demonstrated in this paper based on data provided by inspection reports from City of Tampa. Three main factors, physical, operational, and environmental, were considered during the selection of variables in development of this model. Thirteen independent variables including pipe’s age, material, diameter, flow rate, pipe segment length, depth, slope, soil type, pH, sulfate content, water table, soil hydraulic group, and soil corrosivity were used to build the prediction model. Complications posed by imbalance between condition classes are overcome by changing the classification classes into a binary format (where pipes are in either good or critical structural condition), and then the receiver-operating characteristic (ROC) and confusion matrix were used to measure the performance of the model. The developed model showed 84% accuracy to predict condition of uninspected sewer pipes. The results can be used by utility companies and municipalities to forecast condition of sanitary sewer pipes, schedule inspection times, and make cost-effective decisions to match budget allocations.