Testing the utility of the resampled nSight-2 spectral configurations in discriminating wetland plant species using Random Forest classifier

Abstract

Hyperspectral sensors have the potential of discerning subtle differences among wetland plant species. Assessment of wetland plant species is critical for the effective management of wetland ecosystems. We evaluated the utility of the forthcoming nSight-2 hyperspectral sensor in wetland plant species differentiation, by testing the utility of its spectral settings and compared its performance to EnMap and WorldView-2 sensors in classifying four dominant wetland plant species in Verloren Vallei Nature Reserve, South Africa. For this purpose, we used the Random Forest classifier and field spectrometer data of various wetland plant species. The results showed that the spectral settings of nSight-2, EnMap, and WorldView-2 yielded high overall accuracies of 84.09%, 81.82% and 77.77%, respectively. The best accuracies were achieved with spectral bands sampled across the visible, red-edge and near-infrared spectral regions. Overall, the findings demonstrate the potential of the upcoming hyperspectral satellite missions for wetland ecosystems monitoring and management.