AN IMPROVED AUTOMATIC POINTWISE SEMANTIC SEGMENTATION OF A 3D URBAN SCENE FROM MOBILE TERRESTRIAL AND AIRBORNE LIDAR POINT CLOUDS: A MACHINE LEARNING APPROACH

This work aimed to calibrate FARSITE simulator using a set of wildfires that occurred in north Iranian forests. Fire modeling showed a high potential for estimating spatial variability in fire spread and behavior of the case studies selected. This paper represents a first step in the application of fire spread modeling in northern Iran in wildfire risk monitoring and management. The methodology can be replicated in other Caspian ecosystems to characterize fire spread and behavior.