Comparison of Machine Learning Techniques for Condition Assessment of Sewer Network

Abstract

Assessment of the structural condition of sewer pipes is one of the critical steps in asset management and support investment decisions; therefore, structural condition models with high accuracy are important that can help the utility managers and other authorities correctly assess the current condition of the sewage network and effectively initiate maintenance and rehabilitation strategies. The main objective of this research is to assess the potential application of advanced machine learning (ML) for predicting the structural condition of sewer pipes with a case study in Ålesund city, Norway. Nine physical factors (i.e., age, diameter, depth, slope, length, pipe type, material, pipe form, and connection type) and ten environmental factors (i.e., rainfall, geology, landslide area, building area, population, land cover, groundwater level, traffic volume, distance from the road, and soil type) were used to assess the sewer structural condition employing seventeen ML models. After processing the sewer inspections, 1,159 of 1,449 individual pipelines were used to train the structural condition model. The performance of ML models was validated using the 290 remaining inspected sewer pipes. The area under the Receiver Operating Characteristic (AUC-ROC) curve and accuracy (ACC) showed that the Random Forest (AUC-ROC = 77.6% and ACC = 78.3%) is a sensitive model for predicting the condition of sewer pipes in the study area. Based on the RF model, maps of predicted conditions of sewers were generated that may be useful for utilities and water managers to establish future sewer system maintenance strategies.