Hoping to expedite the process for monitoring water treatment plants as well as making the process easier and less expensive, researchers from the University of Waterloo have designed artificial intelligence (AI) software to help achieve those goals.

The software, according to the research team, is capable of both identifying and quantifying the types of blue-green algae (cyanobacteria) that could force the closure of water systems once it begins to spread.

"We need to protect our water supplies," said Monica Emelko, a professor of civil and environmental engineering and member of the Water Institute at Waterloo. "This tool will arm us with a sentinel system, a more rapid indication when they are threatened.

"The exciting piece is that we've shown testing utilizing AI can be done quickly and well. Now it's time to work through all the possible scenarios and optimize the technology."

To operate, the AI system works in conjunction with a microscope, offering an automatic and inexpensive analysis of water samples for the algae cells in roughly one to two hours — a process, using current methods, that can take up to two days.

Using the AI system, according to the research team, would give early notification to municipalities much sooner than current systems whenever an issue with the water arises.

"This brings our research into a high-impact area," said Alexander Wong, a systems design engineering professor at Waterloo. "Helping to ensure safe water through widespread deployment of this technology would be one of the great ways to really make AI count."

The team predicts that it will take anywhere from two to three years to refine the system, making it available for commercial use.

"It's critical to have running water, even if we have to boil it, for basic hygiene," said Emelko. "If you don't have running water, people start to get sick."

The findings are published in the journal Scientific Reports.