AI helping to fight wildfires

Friday 26 Jan 2024

Researchers in New Brunswick are developing a new approach to tackling Canada's growing threat of wildfires: teaching artificial intelligence to find them faster.

A team of engineers at the Université de Moncton is fine-tuning an algorithm that works with satellite and drone images to detect fires more accurately than humans. The technology also predicts where a blaze will spread, helping firefighters know where to send resources.

Moulay Akhloufi, a computer science professor and head of the Perception, Robotics and Intelligent Machines Laboratory, said it can help spot signs of a fire the human eye would miss. "It's very accurate. Some of the algorithms are able to get to more than 99 per cent performance when we want to detect fires," he said.

After Canada's worst wildfire season on record, forestry and wildfire experts are turning to modelling and satellites as an increasingly important tool. While in early stages of development, some firefighters are already using artificial intelligence to inform decisions on the ground.

"We are using machine learning, when and where appropriate, to do a better job managing wildfires," said wildfire expert Mike Flannigan, of Thompson Rivers University. "It's a very effective tool, though it's not a panacea. It's not going to solve all our problems."

More >>

Source: CBC

Share |

Copyright 2004-2024 © Innovatek Ltd. All rights reserved.