Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Guelph

$42,000.00

Machine Learning/Survival Modeling for Predicting Remaining Service Life of Watermain Pipes

FY 2024-25

Summary
Utilities in Canada are facing the difficult task of replacing watermains while simultaneously ensuring reliable and affordable drinking water to populations within their respective cities.  However, issues of aging infrastructure and the need for efficiency of pipe repair/replacement are becoming increasingly complicated due to constrained budgets and challenges such as ongoing climate change and densification of urban population. Nevertheless, on the positive side, dramatic new insights have been recently gained allowing improved effectiveness using machine learning/artificial intelligence models in combination with survival statistics, a modeling approach used in the life insurance industry. The life insurance models have incorporated right censored information, and hence, when this approach was applied the need no longer existed to not utilize data on water pipes which have not broken (i.e. previous modeling ignored unbroken (the best) pipes). Hence, great improvements in forecasting pipe breaks are demonstrating great potential.  These new insights have just recently been employed, providing the potential to open new vistas of calculation procedures, allowing greatly improved modeling, with much more to learn. Additional insights into such features as the potential merits of alternative pipe types and comparisons of major rehabilitation/replacement techniques are now possible and  hence, proposed in this research.  The expanding array of options warranting consideration will provide important insights into how adjustments in practice have potential to demonstrate and assess both cost-effectiveness and, as well, be protective of the integrity of the watermain pipes, and thereby significantly improve asset management decision-making for water distribution systems for cities in Canada. Additional objectives of this research include: (i) the needs are extremely important to improve options available for small/medium-sized cities since currently, these entities rely strictly on age of pipe for decisions on replacing pipes. Much benefit will be derived by developing an App which will allow use of information currently being learned by large cities to be transformed to these smaller cities/towns to improve their asset management planning; (ii) strategies are also needed which will prioritize pipes thereby improving the robustness and resilience of water distribution system; and, (iii) improved integration of  instrumentation technologies into the machine learning/survival statistics models to include climate change and urban population densification will provide the opportunity to improve asset management as Canadian cities encounter the rapidly occurring changes arising from climate and population density. This research program will be focused on modeling procedures to extend a number of these most valuable insights that have promise to be operationalized and improve decision-making and sustainability of Canada's municipal watermain systems.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-03391
Name nom
McBean, Edward
Department département
School of Engineering
Organization id
24
Institution établissement
University of Guelph
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
42000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
2804
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Expert systems
Research subject fr
Systèmes experts
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Machine Learning/Survival Modeling for Predicting Remaining Service Life of Watermain Pipes
Keywords
machine learning; watermain infrastructure; random survival forest; climate change; asset management plans; risk assessment; data mining; deterioration modeling; lifecycle analysis; risk management
Application summary
Utilities in Canada are facing the difficult task of replacing watermains while simultaneously ensuring reliable and affordable drinking water to populations within their respective cities.  However, issues of aging infrastructure and the need for efficiency of pipe repair/replacement are becoming increasingly complicated due to constrained budgets and challenges such as ongoing climate change and densification of urban population. Nevertheless, on the positive side, dramatic new insights have been recently gained allowing improved effectiveness using machine learning/artificial intelligence models in combination with survival statistics, a modeling approach used in the life insurance industry. The life insurance models have incorporated right censored information, and hence, when this approach was applied the need no longer existed to not utilize data on water pipes which have not broken (i.e. previous modeling ignored unbroken (the best) pipes). Hence, great improvements in forecasting pipe breaks are demonstrating great potential.  These new insights have just recently been employed, providing the potential to open new vistas of calculation procedures, allowing greatly improved modeling, with much more to learn. Additional insights into such features as the potential merits of alternative pipe types and comparisons of major rehabilitation/replacement techniques are now possible and  hence, proposed in this research.  The expanding array of options warranting consideration will provide important insights into how adjustments in practice have potential to demonstrate and assess both cost-effectiveness and, as well, be protective of the integrity of the watermain pipes, and thereby significantly improve asset management decision-making for water distribution systems for cities in Canada. Additional objectives of this research include: (i) the needs are extremely important to improve options available for small/medium-sized cities since currently, these entities rely strictly on age of pipe for decisions on replacing pipes. Much benefit will be derived by developing an App which will allow use of information currently being learned by large cities to be transformed to these smaller cities/towns to improve their asset management planning; (ii) strategies are also needed which will prioritize pipes thereby improving the robustness and resilience of water distribution system; and, (iii) improved integration of  instrumentation technologies into the machine learning/survival statistics models to include climate change and urban population densification will provide the opportunity to improve asset management as Canadian cities encounter the rapidly occurring changes arising from climate and population density. This research program will be focused on modeling procedures to extend a number of these most valuable insights that have promise to be operationalized and improve decision-making and sustainability of Canada's municipal watermain systems.