Using a massive dataset, researchers are developing tools to help them predict when and where wildfires are most likely to start.
The team, led by a Boise State University civil engineering researcher, looked at half a million wildfire starts, and hundreds of attributes about them. Beyond the obvious weather variables like wind speed, temperature and humidity, they also considered human factors like density of development.
Yavar Pourmohamad, a researcher with Boise State University’s civil engineering department, and lead author of a recent paper on the prediction model said the breadth and depth of data points is part of what sets the research apart, and makes it potentially useful to land managers.
“If you are [an] authority and you have limited resources, you want to know where you shouldn't send your resources and where you should send them,” he said.
Pourmohamad said the model could also be used to inform and plan public education or enforcement campaigns around wildfire safety. The paper notes most wildfires are started by people, meaning they are preventable. Human-started fires are also much more likely to damage or destroy structures.
Prevention, he said, is the “most cost-effective” approach to wildfires.
The Boise State researcher said he hopes the work could eventually enable fire danger forecasts on smartphones, similar to mobile weather forecasts.
This story was produced by the Mountain West News Bureau, a collaboration between Boise State Public Radio, Wyoming Public Media, Nevada Public Radio, KUNR in Nevada, KUNC in Northern Colorado, KANW in New Mexico, Colorado Public Radio and KJZZ in Arizona as well as NPR, with support from affiliate newsrooms across the region. Funding for the Mountain West News Bureau is provided in part by the Corporation for Public Broadcasting and Eric and Wendy Schmidt.
