Improving Machine Learning Classifications of Phragmites australis Using Object-Based Image Analysis

Uncrewed aircraft systems (UASs) are a popular tool when surveilling for invasive alien plants due to their high spatial and temporal resolution. This study investigated the efficacy of UAS equipped with three-band (i.e., red, green, blue; RGB) sensor identify Phragmites australis in multiple Minnesota wetlands using object-based image analysis (OBIA) machine learning (ML) algorithms: artificial neural network (ANN), random forest (RF), support vector (SVM). The addition post-ML classification OBIA workflow was tested determine if ML classifications can be improved techniques. Results from each algorithm were compared across sites both without workflow. ANN identified as best classifier not incorporating accuracy 88%. Each three algorithms achieved 91% this suggest that increase ability accurately should used possible. Additionally, decision which use mapping becomes less critical