Ethan Saks | Staff Writer
Featured Image: A new AI model, created by Lassonde professor, will help predict floods. | Courtesy of Jessica Sripaskaran/Excalibur
An Artificial Intelligence (AI) model that can predict potential floods before they occur has been created. This model was created thanks to Lassonde’s Department of Civil Engineering professor Usman T. Khan, and students Everett Snieder and Rahmah Shakir.
Professor Usman KhanThe results came after over a year of research, which focused on combining multiple types of data to predict flood risks for the Bow River and the Don River.
These rivers represent different conditions and demonstrate the flexibility of this technology. Researchers claim that these findings have been more productive with predicting flood risks than past endeavours, and they will let Canadians who live close to a major river breathe a sigh of relief.
“These results outline an approach that can be used to create models with higher accuracy and lower data requirements, which translates to improved flood early warning systems,” said Professor Khan.
“Early warning systems are considered the most effective way to mitigate flood induced hazards.”
These new developments have the potential to save many lives, and can do so before disaster strikes.
Creating an AI-based program to predict flood risk is even more complicated than it already seems. The program combines various types of data to ensure accurate results.
According to YFile, some of these sources include “rainfall, temperature and other flood-related variables to provide the level of the water in the river.”
The types of data will always change depending on where the model is being used and its circumstances.
Implementing this research in other areas of the country will require different types of inputs to be considered.
According to Professor Khan’s article published in the Journal of Hydrology: “Input usefulness is not a binary concept; the correct number of selected inputs is dependent on the desired model complexity.”
In other words, the way this research will be used by others must vary depending on the specific water system, and the region it is being implemented within. Certain factors and input methods will be more important than others depending on a variety of different factors.
Using AI also means that this research can be implemented across the country. Canada, according to Professor Khan, has yet to take advantage of this type of technology. It is difficult to believe that with so many cities surrounded by major rivers and water-networks, our country has not had an accurate method of predicting when a major floor may occur.
This new research will be essential for negating any future risks of flooding; Canadians can rest assured that they will know about any danger far ahead of time.
Perhaps these new developments will also have benefits for other countries around the world, but for now, some Canadians are safer due to Professor Khan’s research.
