JERUSALEM, March 2 (Xinhua) -- Israeli researchers have developed an artificial intelligence (AI) mapping method to predict and prevent forest fires, Bar Ilan University (BIU) in central Israel said on Tuesday.
"Mapping fire-prone areas is important for both fire prevention and firefighting efforts, and using satellite-based insights and AI may improve dealing with these tasks," BIU noted.
Existing static maps for forecasting fires, based on topography, vegetation density and humidity, are missing some important factors that can affect fire occurrence and spread.
Thus, BIU researchers have investigated the impact of two satellite-derived metrics that represent long-term vegetation status and dynamics on fire-risk mapping.
One index is the woody density at the grid cell, while the other index is the five-year trend of dryness in the woody vegetation.
The researchers used wildfires that occurred in Greece in 2007 to perform the analysis and found, using three machine learning algorithms, that both indexes improved the fire-risk map.
"The new method may produce more accurate fire-risk maps and can provide important information on plant dynamics that may be used in fire-behavior models," BIU concluded.