U of G Research Looks at How to Avoid Burning Up Wildfire Resources

In the first few moments after a wildfire sparks, the form and speed of the reaction are crucial.

Mobilizing aircraft is one of the first steps, and new research from the University of Guelph is evaluating past responses to better prepare for wildfires in British Columbia.

In collaboration with Natural Resources Canada, Dr. College of Engineering and Physical Sciences statistics professor Khurram Nadeem used historical data from the BC Wildfire Service (BCWFS) to develop new models for wildfire managers when making initial decisions about using aircraft attacks (the initial response to an active wildfire) .

The results were recently published in the International Journal of Forest Fires.

According to data collected between 1986 and 2014 analyzing more than 70,000 wildfires, there are an average of 1,758 wildfires per year in British Columbia.

First attack aircraft have been deployed on more than 40 percent of those fires and account for 20 percent of the province’s annual firefighting budget, which ranges from $20 million to $120 million. In total, Canada spends $500 million annually on wildfire aviation.

The development of forecast models will help wildfire managers to optimally position the right number of aircraft in strategic geographic locations, saving financial resources and reducing risk to people and ecosystems threatened by a fast-moving wildfire.

Canada, climate change and wildfire risk

This study only focuses on BC because it was the province with the most historical data. The models developed can be applied across Canada to any region experiencing wildfires, Nadeem said.

As climate change exacerbates the number of wildfires every year, Nadeem said, this research is vital. “This is a stark warning of global warming,” he said. “We developed this methodology as a set of quantitative tools to help managers.”

Using the wildfire data, the researchers also examined 250,000 flights recorded by the BCWFS Aircraft Management System and weighted variables such as flight dates, aircraft models, registration numbers, operating hours and number of routes flown, and the Fire Weather Index (FWI).

“The novel aspect of the model is that it quantifies the response in the past and, given that, predicts whether or not you’re going to use an airplane,” explained Nadeem.

Digging into the data to analyze fire safety decisions spanning three decades was like “detective work,” Nadeem said. “Through quantitative modeling, you learn to reduce waste, which in turn improves your overall system, including your response time, and reduces risk.”

A new model for avoiding tragedies like the Lytton, BC wildfire

Experienced wildfire managers position planes where they’re likely to be needed most and usually make successful decisions, Nadeem said. That may mean the first attack aircraft will be stationed at a specific location a few days in advance, depending on how fire weather conditions might develop.

The strategic placement of aircraft allows for a faster physical response to a wildfire, allowing managers to focus on decisions about personnel, fire suppression distribution, and other responsibilities. “You can make quicker decisions once you have the plane stationed nearby,” Nadeem said, which may help avoid tragedies like that in Lytton, BC, a village that burned to the ground within hours in June 2021.

Armed with this research, wildfire managers can now base a response from a hybrid perspective; This is human-machine learning integration, Nadeem said. “Statistical learning and human decision-making go hand in hand,” he explained.

“That’s the hybrid approach that I think would really reduce risk and hopefully prevent incidents like the one at Lytton.”

Contact:

dr Khurram Nadeem
[email protected]