Coupled Dynamic Data-Driven Framework for Forest Fire Spread Prediction

Predicting the potential danger of a forest fire is an essential task of wildfire analysts. For that reason, many scientists have focused their efforts on developing propagation models that predict forest fire evolution to mitigate the consequences of such hazards. These propagation models require a precise knowledge of the whole environment where the fire is taking place. In the context of natural hazards simulation, it is well known that, part of the final forecast error comes from the uncertainty in the input data. In this work, we use a Dynamic Data-driven methodology to overcome such problem. The core of the methodology is a calibration stage previous to the forecast where complementary models, data injection and intelligent systems are working in a symbiotic way to reduce the forecast errors at real time. This approach has been tested using a forest fire that took place in Arkadia (Greece) in 2011.