Artificial intelligence may soon be used to help predict extreme fire weather to better prepare provinces for devastating wildfires.

According to the Edmonton Journal, researchers from the University of Alberta and University of Oklahoma teamed up to study how real-time meteorological data inside a neural network could be used to create early warning systems.

Their research was recently published in the Canadian Journal of Forest Research.

In their work, a computer model compared the most current atmospheric data with what it has learned from 53 years worth of historic data already in its “brain.” It produced a self-organizing map that identified patterns in ridges and troughs to predict extreme fire weather for the next day, next week or next fortnight.

The new system would be used in tandem with existing prediction, said Mike Flannigan, the study’s co-author and a U of A professor.

Read the Edmonton Journal story here.