North America’s water distribution systems are aging and incurring increased pipe breaks. These breaks pose a serious threat to urban drinking water security, leading to service interruptions, loss of revenue, and increasing risk of water contamination. Prediction models have been developed to help identify when individual underground water pipes are expected to break, helping utilities develop pipe renewal projects and avoid costly pipe breaks that impact water supply reliability. This paper provides an in-depth comparison of the two leading statistical pipe-break modeling methods: machine-learning and survival-analysis algorithms. A gradient-boosting decision tree machine-learning model and a Weibull proportional hazard survival-analysis model are used to predict time to next break for cast-iron pipes in a major Canadian water distribution system. Results indicate that removal of censored events from the machine-learning model biases the model to predict earlier pipe breaks than occur. Overall, water utilities concerned with short-term security arising from impacts of pipe breaks on water security may favor the machine-learning approach, but the survival-analysis models’ ability to incorporate right-censored data makes it more appropriate for long-term asset management planning.

In the threshold of the appearance of global warming from theory to reality, extensive research has focused on predicting the impact of potential climate change on water resources using results from Global Circulation Models (GCMs). This research carries this further by statistical analyses of long term meteorological and hydrological data. Seventy years of historical trends in precipitation, temperature, and streamflows in the Great Lakes of North America are developed using long term regression analyses and Mann-Kendall statistics. The results generated by the two statistical procedures are in agreement and demonstrate that many of these variables are experiencing statistically significant increases over a seven-decade period. The trend lines of streamflows in the three rivers of St. Clair, Niagara and St. Lawrence, and precipitation levels over four of the five Great Lakes, show statistically significant increases in flows and precipitation. Further, precipitation rates as predicted using fitted regression lines are compared with scenarios from GCMs and demonstrate similar forecast predictions for Lake Superior. Trend projections from historical data are higher than GCM predictions for Lakes Michigan/Huron. Significant variability in predictions, as developed from alternative GCMs, is noted. Given the general agreement as derived from very different procedures, predictions extrapolated from historical trends and from GCMs, there is evidence that hydrologic changes particularly for the precipitation in the Great Lakes Basin may be demonstrating influences arising from global warming and climate change.

Effective management of aging water distribution infrastructure is essential for preserving the economic vitality of North American municipalities. Historical failures within Scarborough, Ontario, Canada, reveal a seasonal pattern to water main failures, with the majority of failures occurring during the very cold winter months. Extensive installation of cement mortar lining and cathodic protection have extended the life span of aging water mains and reduced escalating failure rates. Artificial neural networks are found to be capable of predicting the time to failure for individual pipes using a range of pipe-specific attributes, including diameter, length, soil type, construction year, and the number of previous failures. The developed models have correlation coefficients ranging from 0.70–0.82 on instances reserved for evaluating predictive performance and have utility on an asset-by-asset basis when planning water main inspection, maintenance, and rehabilitation. Simulated failure scenarios ind...