Start small and scale up. Companies, organizations and water utilities that have successfully integrated AI started with small projects that delivered fast results. The approach allows for building confidence in the technology and how to scale it. Identify specific operational challenges that AI might be able to support. “You have to look at what do you have, and do you have what you need to build a model in that area and is that something that could be automated,” says Joshua Goldman, with Metro Water Recovery.
Consider a free trial for AI that can address a specific problem and demonstrate success before full deployment. However, when using a free trial, be wary about what information you’re sharing, and whether it will be kept confidential. Already, vendors have developed programs to help water utilities and others with predictive maintenance, capital improvement planning, automated water quality monitoring, and energy optimization at large pumping stations, says Jim Fitchett, with VODA.ai, which is deploying its water main repair prediction program in Greeley. He also suggests looking for vendors offering solutions that fit well within existing systems, rather than ones that require a full overhaul.
Watch for the opportunities that come your way. Metro Water Recovery built a reputation for engaging with new technologies, and so has been approached by several vendors about participating in new projects, some of which had secured outside funding.
Integrate new technology when replacements are due. Breckenridge Water Division last replaced water meters in 2005, so was due for an upgrade. The division also enlisted the help of an energy performance contractor to review options and found that new meters with acoustic leak detection would solve a known problem: a high volume of unaccounted for water. With a wave of retirements expected at many facilities and even at farms, AI can also help preserve institutional knowledge by capturing what those soon-to-be retirees know.
Look for ways for AI to add to existing staff expertise, not replace it. Successful deployments focus on providing operators with more and better information. “We call it augmented intelligence,” Fitchett says. “It amplifies what people can do, not replaces them.”
Independent journalist Elizabeth Miller writes about environmental issues in the American West for publications including The Washington Post, Scientific American, Outside, Backpacker, and The Drake.
Print