A Review of Genetic Algorithm Approaches for Wildfire Spread Prediction Calibration

Wildfires are complex natural events that cause significant environmental and property damage, as well human losses, every year throughout the world. In order to aid in their management mitigate impact, efforts have been directed towards developing decision support systems can predict wildfire propagation. Most of available tools for spread prediction based on Rothermel model that, apart from being relatively computing demanding, depends several input parameters concerning local fuels, wind or topography, which difficult obtain with a minimum resolution degree accuracy. These factors leading causes deviations between predicted fire propagation real this sense, paper conducts literature review optimization methodologies use evolutionary algorithms parameter set calibration. present review, it was observed current calibration is mostly focused genetic (GAs). Inline trend, presents an application model’s parameters, namely: surface-area-to-volume ratio, fuel bed depth, moisture, midflame speed. The GA validated 37 datasets obtained through experimental prescribed fires controlled conditions.