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.

Many water utilities are facing a crisis of aging infrastructure. Aging pipes are deteriorating, and pipe breaks are increasing. A variety of pipe break prediction models have been developed to identifying which pipes are most likely to break next, in order to assist utilities in prioritizing pipe replacement. This paper investigates the role of data in pipe break prediction model accuracy. A gradient boosting decision tree machine learning model, a Weibull proportional hazard probabilistic model and two ranking models (based on ‘age of pipe’ and ‘previous-break’) were calibrated using a various number of pipes, years of break records and input variables. The results indicate how the different model types are impacted by data limitations. Overall, this study finds the Age-based approach to be inaccurate, and the XGBoost machine learning model demonstrates superior predictive capability when the training dataset contains more than 5 years of break records and 2,000 or more pipes.

Distribution systems throughout North America are deteriorating and pipe breaks are increasing. To deal with these infrastructure crises, utilities have begun to adopt proactive pipe replacement models to determine which pipes to replace and when. This paper develops the first random survival forest watermain pipe replacement model that incorporates survival analysis techniques into a machine learning framework, avoiding major limitations associated with other popular models. The random survival forest (RSF) model ($\mathrm{C}\text{-}\mathrm{index}=0.880$ ) employed in this paper outperforms the Weibull proportional hazard survival model ($\mathrm{C}\text{-}\mathrm{index}=0.734$ ) and the random forest machine learning model ($\mathrm{C}\text{-}\mathrm{index}=0.807$ ). The results indicate that by adopting the RSF model, a utility avoids costly early pipe replacement, with a case study suggesting a reduction in pipe replacement and repair costs by 14% over the next 50 years. Overall, the findings indicate that by adopting the RSF algorithm, which incorporates right-censored break data, a utility would be able to more accurately predict future pipe breaks, spread out pipe replacement over a longer range of years, and identify financial savings available from a more effective pipe replacement strategy.

The Severe Acute Respiratory Syndrome Coronavirus 2 pandemic has challenged medical systems to the brink of collapse around the globe. In this paper, logistic regression and three other artificial intelligence models (XGBoost, Artificial Neural Network and Random Forest) are described and used to predict mortality risk of individual patients. The database is based on census data for the designated area and co-morbidities obtained using data from the Ontario Health Data Platform. The dataset consisted of more than 280,000 COVID-19 cases in Ontario for a wide-range of age groups; 0–9, 10–19, 20–29, 30–39, 40–49, 50–59, 60–69, 70–79, 80–89, and 90+. Findings resulting from using logistic regression, XGBoost, Artificial Neural Network and Random Forest, all demonstrate excellent discrimination (area under the curve for all models exceeded 0.948 with the best performance being 0.956 for an XGBoost model). Based on SHapley Additive exPlanations values, the importance of 24 variables are identified, and the findings indicated the highest importance variables are, in order of importance, age, date of test, sex, and presence/absence of chronic dementia. The findings from this study allow the identification of out-patients who are likely to deteriorate into severe cases, allowing medical professionals to make decisions on timely treatments. Furthermore, the methodology and results may be extended to other public health regions.

The numbers of novel coronavirus cases continue to grow at an unprecedented rate across the world. Attempts to control the growth of the virus using masks and social-distancing, and, recently, double-masking as well, continue to be difficult to maintain, in part due to the extent of asymptomatic cases. Analyses of large datasets consisting of 219,075 individual cases in Ontario, indicated that asymptomatic and pre-symptomatic cases are substantial in number. Large numbers of cases in children aged 0–9 were asymptomatic or had only one symptom (35.0% and 31.4% of total cases, respectively) and resulted in fever as the most common symptom (30.6% of total cases). COVID-19 cases in children were more likely to be milder symptomatic with cough not seen as frequently as in adults aged over 40, and past research has shown children to be index cases in familial clusters. These findings highlight the importance of targeting asymptomatic and mild infections in the continuing effort to control the spread of COVID-19. The Pearson correlation coefficient between test positivity rates and asymptomatic rates of −0.729 indicates that estimates of the asymptomatic rates should be obtained when the test positivity rates are lowest as the best approach.

North America is facing an aging watermain infrastructure crisis. Pipes are surpassing their expected service life, and surveys continue to suggest that the rate of pipe breaks is increasing dramatically. This paper investigates two utilities in Ontario, Canada, that have managed to halt, and even decrease, break rates substantially over the last two decades. Specifically, the impact of adopting early rehabilitation for both cities, including hot-spot cathodic protection, retrofit cathodic protection, lining, early adoption of PVC, and proactive pipe replacement are examined. A random survival forest model is developed for major pipe cohorts for both cities, and using this machine-learning survival analysis model, the numbers of breaks avoided due to pipe rehabilitation are examined. The results indicate pipe rehabilitation techniques avoided 14,572 breaks between 1986 and 2015 for City A and 764 breaks between 1990 and 2020 for City B, and, in the absence of these undertakings, incurred break rates would have been more than 50% greater for both cities. Therefore, pipe rehabilitation is a major factor that has resulted in the declining break rates identified in both cities, suggesting that other cities struggling with increasing break rates should consider similar rehabilitation strategies.