Integrating dynamic features into machine learning models for predicting sewer network failures: a Random Forest approach

Sewer blockages and flooding remain persistent challenges. Water utilities often deploy labour-intensive, iteratrive approaches, such as repeated CCTV inspections and jetting, to detect and address these problems. Recently, machine learning (ML) based asset failure prediction has emerged as a cost-effective alternative, enabling proactive identification of vulnerable pipe sections that can then be the focus for inspection and intervention. Early ML-based predictive models primarily focused on non-dynamic factors, such as physical pipe attributes, while newer approaches have incorporated dynamic variables like rainfall and pipe flow, resulting in significant accuracy improvements. This study examines the integration of sediment transport mechanics, using network hydraulic model derived parameters, into a predictive Random Forest (RF) model. Results demonstrate that incorporating dynamic features representing sediment transport capacity and its spatial variation considerably enhances the RF model’s predictive power, offering a more reliable tool for identifying and managing blockages, and flooding in combined sewer networks.