Mapping Invasive Phragmites australis Using Unoccupied Aircraft System Imagery, Canopy Height Models, and Synthetic Aperture Radar

Invasive plant species are an increasing worldwide threat both ecologically and financially. Knowing the location of these invasive infestations is first step in their control. Surveying for Phragmites australis particularly challenging due to limited accessibility wetland environments. Unoccupied aircraft systems (UAS) a popular choice management ability survey environments high spatial temporal resolution. This study tested utility three-band (i.e., red, green, blue; RGB) UAS imagery mapping St. Louis River Estuary Minnesota, U.S.A. Saginaw Bay Michigan, Iterative object-based image analysis techniques were used identify two classes, Not Phragmites. Additionally, effectiveness canopy height models (CHMs) created from data types, commercial satellite stereo retrievals, RADARSAT-2 horizontal-horizontal (HH) polarization identification. The highest overall classification accuracy 90% was achieved when pairing with UAS-derived CHM. Producer’s class ranged 3 76%, user’s accuracies above 90%. had producer’s 88%. Inclusion HH caused slight reduction accuracy. Commercial retrievals increased commission errors decreased resolution vertical lowest seen using only RGB imagery. promising identification, but should be conjunction