Decision-makers rely on a “best practice” of prioritizing actions based on pipe age, material, and failure history, but this method is outdated. It works, but it ignores many significant variables. Soil type, moisture, weather, land use, seismic activity, proximity to roads, bridges, bodies of water, railroads, and others impact remaining useful life. The mosaic of geography, geology, topography, pipe materials, contractor skills, and proactive maintenance impact asset health.
Machine learning, a subset of artificial intelligence (AI), offers a new “best practice” by considering dozens of variables to accurately assess the probability of failures. Machine learning finds patterns that precede failures, removes bias, and consistently predicts future events. It helps utilities prevent half their water main breaks, predict wastewater incidents, and find lead service lines.
Machine learning can improve asset management, detect leaks, predict failures, and optimize resources. Asset management based on science provides better leverage for addressing the many challenges in water distribution and wastewater collection systems. Utilities can easily avoid half of their water main failures using machine learning.
Potential benefits include the following:
This is the first article in our AI for Utilities series – where we break down what AI and machine learning really means, how it works, how it helps, and what results utilities are seeing. We also bust the myths around this often mystified technology.
🔔 Subscribe to our blog so you don’t miss the next chapter.