A rapid and accurate method of mapping invasive genotypes using Sentinel-2 images.

Background: The management of invasive genotypes depends on reliable and accurate information of their extent and distribution. This study investigated the utility of the multispectral Sentinel-2 imageries to map infestations of the invasive along three riparian ecosystems in the Western Cape Province of South Africa.

Methods: The Sentinel-2 image was acquired from the GloVis website (http://glovis.usgs.gov/). Random forest (RF) and support vector machine (SVM) algorithms were used to classify and estimate the spatial distribution of invasive genotypes and other land-cover types in three riparian zones . the Leeu, Swart and Olifants rivers. A total of 888 reference points comprising of actual 86 GPS points and additional 802 points digitized using the Google Earth Pro free software were used to ground-truth the Sentinel-2 image classification.

Results: The results showed the random forest classification produced an overall accuracy of 87.83% (with kappa value of 0.85), while SVM achieved an overall accuracy of 86.31% with kappa value of 0.83. The classification results revealed that the invasion was more rampant along the Olifants River near De Rust with a spatial distribution of 913.39 and 857.74 ha based on the RF and SVM classifiers, respectively followed by the Swart River with coverage of 420.06 ha and 715.46 hectares, respectively. The smallest extent of invasion with only 113.52 and 74.27 hectares for SVM and RF, respectively was found in the Leeu River. Considering the overall accuracy of 85% as the lowest benchmark for a robust classification, the results obtained in this study suggests that the SVM and RF classification of the Sentinel-2 imageries were effective and suitable to map invasive genotypes and discriminate them from other land-cover types.