/ News / BlueConduit Unveils Innovative Predictive Modeling for Water Mains

BlueConduit Unveils Innovative Predictive Modeling for Water Mains

Parul Dubey on June 12, 2024 - in News, Products, Technology

(ANN ARBOR, Mich.) — BlueConduit, a leading provider of digital solutions for the water industry, has launched its newest offering: water main prediction technology. Building on the success of its predictive models for lead service lines, BlueConduit is extending its expertise to help cities and water systems tackle the challenges of water main management, condition assessment, and replacement with advanced data science and AI-enabled process and technology solutions.

According to a December 2023 Utah State University Water Research Laboratory study, there are more than 2 million miles of water mains in the U.S. and Canada, costing $2.6 billion annually in maintenance and repair costs. BlueConduit’s predictions for water mains will help water utilities forecast likely water main breaks, leaks and potential impacts on service levels; assess risk; and determine which high-risk mains are candidates for more expensive, intrusive physical condition assessment or immediate removal.

BlueConduit has always been at the forefront of predictive analytics for water systems, enabling communities to make informed, data-driven decisions that positively affect public health. “BlueConduit is setting a new standard for predictive modeling for water main management and replacement,” said Lorne Groe, CEO of BlueConduit. “It’s estimated that over a quarter million water main breaks occur each year. With our new water main prediction capabilities, we’re helping communities manage their water mains more efficiently by predicting leaks and failures before they happen.”

BlueConduit’s water main prediction technology leverages advanced AI and human expertise, representing a milestone in developing water management solutions. This technology stands out by offering flexible, locally tailored models that integrate seamlessly with water systems’ existing ESRI platforms, unlike competitors’ static predictions or the requirement for separate platforms.

“It’s the product of the same brilliant data scientists who developed our lead service lines technology,” Groe said. “Our team employs the best statistical and machine learning practices, driven by a passion to ensure that decisions made by our customers are not only informed but also equitable and sustainable. This approach highlights how integrating technology with the expertise of people can significantly enhance the utility of existing data management tools in water systems.”

The custom localized models offered by BlueConduit are enriched with outside information, such as weather patterns, soil types and other relevant metrics, ensuring high accuracy and relevance. This approach allows for predictions across variable time horizons, from a single month up to 5+ years, granting flexibility to asset managers in both short- and long-term planning.

“Our water main predictions stand apart not just for the technology behind them, but for how they’re delivered directly into the hands of those who need them, in the format they use every day,” Groe added.

Visit BlueConduit’s booth at the American Water Works Association ACE24 Conference in Anaheim, California, from June 10-13 to view a demo of the new water main prediction technology. For more information, visit BlueConduit.com.

###

About BlueConduit
BlueConduit is the leading water analytics and technology company pioneering the use of predictive modeling for water system decision making and planning. Utilities, municipalities, government agencies, and engineering firms lean on BlueConduit’s tools and technology to efficiently manage service line material inventories, lead line replacement, and water main condition assessment. Utilizing advanced AI and machine learning algorithms, paired with an expert team and rigorous process, BlueConduit’s approach empowers communities to make more efficient, equitable and sustainable decisions about their water systems.

Comments are disabled