Web based AI-enabled tool
that empowers your data
Article 1 - 1% R&R plan too much? Not enough?
Concerned a 1% R&R rate for your water pipes is too much? Consider an alternative approach that can save up to 80% in R&R over the next 12 years. View Article
Article 2 - Desktop scoring vs. advanced analytics to determine the LOF of a pipe
Are you still using Desktop Scoring to assess the Likelihood of Failure of pipes? Machine Learning is a better alternative, more accurate, easier to use, affordable. View Article
Article 3 - Case Studies - Desktop scoring vs. advanced analytics to determine the LOF of a pipe
The capacity of our machine learning model to predict breaks is up to 6 times superior to desktop scoring. Read about our 3 case studies applying machine learning to 3 systems of different size, physical condition, data quality, and break history. View Article
Article 4 Machine Learning to Predict Water Pipe Breaks - Data Needed
This article defines the data needed to predict water main breaks using machine learning.
Article 5- Machine Learning to Predict Water Pipe Breaks - Abandoned Pipes
The reality is that you may be underestimating how soon your pipes will break if the
abandoned pipes are not taken into account in the pipe break analysis.
Article 6- Incidental Data Issues - Missing and Incoherent Values
Pipes and breaks with issues weaken break predictions. It is therefore important to limit their number.
Article 7- Structural Data Issues
The promise of machine learning is that break predictions will get better as more data become available. However, if structural flaws in data processes exist, over time, break predictions may actually become worse.
Article 8 CMMS Turn your New CMMS into a Ally of your AI-powered Break Predictions Model
Many water utilities are currently transitioning or will soon move from an old legacy Computerized Maintenance Management System (CMMS), sometimes built in house, to a new more modern enterprise system. A CMMS is the depository where the work orders and breaks are collected, stored and managed.