Scientists from the University of Waterloo have developed an artificial intelligence (AI) monitoring technology for monitoring the health of the water at water treatment plants. The new monitoring system is cheaper and easier than the traditionally used methods and keeps the public safe.
The new AI software can quickly identify and quantify different kinds of cyanobacteria (blue-green algae). Cyanobacteria is a threat to public health as well as a threat to the system because it can shut the water treatment plants shut down.
"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."
The AI system uses software with a microscope to analyze water samples from the water treatment plants in one to two hours. Within this time, the samples are analyzed by the AI system and those results are confirmed by a human analyst. Some automated systems like this already exist, but they need extremely expensive equipment and supplies.
The currently used testing methods require workers to send samples out to a lab for manual analysis by scientists. These methods are effective but it can take one or two days to receive the results and at that point, the whole water treatment plant may already be contaminated.
The new system provides wastewater plants with early warning of potential problems because the testing can be done quickly and frequently.
"This brings our research into a high-impact area," said Wong. "Helping to ensure safe water through widespread deployment of this technology would be one of the great ways to really make AI count."
Researchers say to fully commercialize the sample testing system may take two to three years. Developing the AI system that has continuous monitoring could take three to four years to fully develop and commercialize.
"It's critical to have running water, even if we have to boil it, for basic hygiene," said Monica Emelko, a professor of civil and environmental engineering at Waterloo. "If you don't have running water, people start to get sick."
The paper on the new AI system was published in Scientific Reports.