… Likewise, machine learning models provide various degrees of interpretability, from the … of
machine learning models to bring additional insights into the causal analysis of pipe breaks by …

… in developing machine learning models to … pipe breaks. To overcome the limitation of data
availability, this article presents a case study exploring the performance of machine learning …

… We built a Machine Learning system to assess the risk of a water mains breaking. Using …
past main breaks, pipe age, and pipe diameter, pipe material are important in predicting a main …

… renewal projects and avoid costly pipe breaks … pipe-break modeling methods: machine-learning
and survival-analysis algorithms. A gradient-boosting decision tree machine-learning …

… for the left-truncation issue in pipeline failures. To resolve or mitigate the impact of left
truncation on pipe break data, machine learning imputation methods are used in this study. …

… mains by responding to failures or proactively choosing pipes likely to fail. Machine learning
can find fragile pipes more accurately than using age or historical breaks as indicators. …

… To balance the dataset, the oversampling method [64] is used in this study, which randomly
replicates the minor class of pipe break dataset until the number of break samples equals the …

… application of a machine learning framework designed to systematically analyze the link
between CPIS and pipe breaks. Acknowledging the role of water pressure in these breaks, we …

… of these factors are important to identify the priority of pipe renewals. Ultimately, we believe
this work, at the intersection of Machine Learning and Asset Management, will lead to more …

… as machine learning algorithms to predict pipe breaks. However, unlike statistical survival
analysis models, standard machine learning … data that are prevalent in pipe break datasets. …