< BACK TO ALL PRESENTATIONS

Michael Gloven, Expert Infrastructure Solutions (EIS)

Aging physical assets such as energy pipelines, water and waste water systems, roads, bridges, railways and communication networks are faced with investment challenges to ensure they meet on-going service, reliability, safety and compliance requirements. This session presents a case study demonstrating a risk-based investment decision-making approach supported by machine learning for water distribution system assets. According to the latest ASCE report on US water and waste water infrastructure, an estimated $1 trillion is necessary to maintain and expand service over the next 25 years to ensure a safe, reliable drinking water supply. Machine learning is a method to support targeted renewal and prioritization of this infrastructure spend through data driven assessment of asset criticality and likelihood of failure.