Monitoring Invasive Plant Species Using Hyperspectral Remote Sensing Data

The species richness and biodiversity of vegetation in Hungary are increasingly threatened by invasive plant brought from other continents foreign ecosystems. These have spread aggressively the natural semi-natural habitats Europe. Common milkweed (Asclepias syriaca) is one that pose greatest ecological menace. Therefore, primary purpose present study to map monitor common milkweed, most Furthermore, possibilities detect validate this special analyzing hyperspectral remote sensing data were investigated. In combination with field reference data, high-resolution aerial images acquired an unmanned vehicle (UAV) platform 138 spectral bands areas infected examined. Then, support vector machine (SVM) artificial neural network (ANN) classification algorithms applied highly accurate data. As a result, individuals distinguished images, achieving overall accuracy 92.95% case supervised SVM classification. Using ANN model, 99.61% was achieved. To evaluate proposed approach, two experimental tests conducted, both cases, we managed distinguish individual specimens within large variety spreading area 2 ha, based on centimeter spatial resolution UAV imagery.