An evolution of statistical pipe failure models for drinking water networks: a targeted review

The use of statistical models to predict pipe failures has become an important tool for proactive management of drinking water networks. This targeted review provides an overview of the evolution of existing statistical models, grouped into three categories: deterministic, probabilistic and machine learning. The main advantage of deterministic models is simplicity and relative minimal data requirement. Deterministic models predicting failure rates for the network or large groups of pipes performs well and are useful for shorter prediction intervals that describe the influences of seasonality. Probabilistic models can accommodate randomness and are useful for predicting time to failure, interarrival times and the probability of failure. Probability models are useful for individual pipe models. Generally, machine learning describes large complex data more accurately and can improve predictions for individual pipe failure models yet are complex and require expert knowledge. Non-parametric models are better suited to the non-linear relationships between pipe failure variables. Census data and socio-economic data requires further research. The complexity of choosing the most appropriate statistical model requires careful consideration of the type of variables, prediction interval, spatial level, response type and level of inference is required.