Fusion of Remotely-Sensed Fire-Related Indices for Wildfire Prediction through the Contribution of Artificial Intelligence

Wildfires are a natural phenomenon, which nowadays, due to the synergistic effect of increased human intervention and escalation climate change, displaying an ever-increasing intensity frequency. The underlying mechanisms present complexity, with phenomenon itself being characterized by significant degree stochasticity. For above reasons, machine learning models neural networks implemented. In current study, two types implemented, namely, Artificial Neural Networks (ANN) Radial Basis Function (RBF). These utilize information from Fire Weather Index (FWI), Fosberg (FFWI), Normalized Difference Vegetation (NDVI) Moisture (NDMI), aiming predict ignitions in region Greece. All indices have been developed through Google Earth Engine platform (GEE). addition, new index is proposed named “Vegetation-Enhanced FWI” (FWIveg) order enhance FWI vegetation NDVI. To increase robustness methodology, genetic algorithm-based approach was used obtain algorithms for calculation index. Finally, artificial network implemented Mati wildfire Attica, Greece (23 July 2018) applying FWIveg, assess both effectiveness as well ability ignition events using networks. Results highlight providing joint fire prediction intelligence-based approaches.