EDMONTON — As wildfires become more common amid hot, dry conditions around the world, a new data analysis model from the University of Alberta found one particular strategy is key in the crucial first hours of a moderately difficult wildfire: loading the front lines with more firefighters.
The study, led by Ilbin Lee, an operations management professor in the Alberta School of Business, aims to improve the initial attack against fires in Alberta, and suggests the tactic is the best use of already stretched resources.
Lee’s team analyzed the wildfire fighting data of more than 13,000 fires in Alberta during a 15 year timespan to consider how the amount of resources used in the initial attack — essentially the first day of firefighting — affected the ability to have the fire under control, or held, by day two. The results suggest targeting wildfires classified as medium difficulty, which account for 19.6 per cent of all fires. Historically, agencies fighting these fires used 48.3 work-hours of firefighters on the first reported day of the fire.
The group also developed a machine learning model to predict whether a new fire belongs to the target group, enabling a proactive strategy. The results show that if managers can increase the size of the initial attack by 64 work-hours for those fires identified by machine learning, then the initial attack success rate for the target fires will improve from 92.2 per cent to 96.2 per cent.
“Think of this as 16 more people at four hours each,” explains Lee.
The improvement is more pronounced for fires on the “harder” side of medium difficulty, which account for 6.3 per cent of all fires. Using the same strategy would increase the success rate from 86.9 per cent to 95.4 per cent.
Lee notes that targeting medium difficulty fires is fairly intuitive because efforts to fight less difficult fires are very likely to succeed with the current level of effort, as opposed to the toughest wildfires where early suppression success is unlikely.
Besides applying his operations management expertise to wildfires, Lee also uses machine learning techniques to derive implications for policy-making and design to improve the efficiency of hospitals.
To speak with Ilbin Lee, please contact:
Michael Brown, U of A media specialist
michael.brown@ualberta.ca | 780-977-1411