Ontario Water Consortium - WIG Project Highlight: Using machine learning to make flood forecasts less wishy-washy
“Studies show that machine-learning models are extremely good at predicting stream flow discharge. They tend to perform better and run faster than physical models. On top of that, you don’t need to train machine-learning models using data from a specific watershed — just data from a sufficiently large number of other watersheds.”
An AI-produced visual displaying a 3D river model accompanied by a flood forecasting system powered by machine learning algorithms.
Click here to read the article on the Ontario Water Consortium
The Ontario Water Consortium has written an excellent article which reviews Aquanty’s latest technology driven initiative that can be used to manage water resources. With support from the Ontario Water Consortium’s Water Industry Growth Program, Aquanty is making machine-learning (i.e. artificial intelligence) driven real-time flood forecasting a reality. As climate change increases the frequency and intensity of extreme weather, flood forecasting is becoming increasingly important. But creating accurate predictions has never been easy, and shifting precipitation patterns only add to the challenge. Now, AI offers new ways to address those challenges. With a grant from OWC’s Water Industry Growth (WIG) program — which funds the development of new water technologies by Ontario companies — Aquanty has developed a new machine-learning model that can produce highly accurate predictions hours or even months into the future (forecast skill may vary). We are currently working on integrating these new capabilities into our suite of web-based water decision support tools. As one of the only companies in Canada currently doing this kind of forecasting, we are well positioned to meet a growing need for advanced forecasting tools.
ML-based streamflow forecasts are currently available for a small selection of watersheds in southwestern Ontario through Aquanty’s HGSRT web platform.
Click here to read the article on the Ontario Water Consortium
“What we’re working towards essentially is putting the pieces in place so that we can combine the best strengths of both the physics-based approach to modeling and the machine-learning-based approach to forecasting stream flows,”