Unmanned Aerial Vehicle (UAV)-Based Mapping of Acacia saligna Invasion in the Mediterranean Coast

Remote Sensing (RS) is a useful tool for detecting and mapping Invasive Alien Plants (IAPs). IAPs on dynamic heterogeneous landscapes, using satellite RS data, not always feasible. Unmanned aerial vehicles (UAV) with ultra-high spatial resolution data represent promising detection mapping. This work develops an operational workflow Acacia saligna invasion along Mediterranean coastal dunes. In particular, it explores tests the potential of RGB (Red, Green, Blue) multispectral (Green, Red, Red Edge, Near Infra—Red) UAV images collected in pre-flowering flowering phenological stages A. saligna. After ortho—mosaics generation, we derived from DSM (Digital Surface Model) HIS (Hue, Intensity, Saturation) variables, calculated NDVI (Normalized Difference Vegetation Index). For classifying two built set raster stacks which include different combination variables. image classification, used Geographic Object-Based Image Analysis techniques (GEOBIA) Random Forest (RF) classifier. All classifications information (collected combinations variables) produced maps acceptable accuracy values, higher performances classification period images, especially + combination. The adopted approach resulted efficient method early IAPs, also complex environments offering sound support to prioritization conservation management actions claimed by EU IAS Regulation 1143/2014.