Band Combinations Application for Discrimination of Cirsium arvense and Stachys byzanthina Distribution

Invasion by invasive species is an ecosystem level problem in restoration. Invasive species present a threat to the restoration of many natural areas and often drive ecological changes that may be irreversible and thus preclude successful restoration. Invasion prevention, early detection and removal of these species are key to their control and management. This paper aims to investigate the efficiency of different band combinations of Landsat TM image in identifying invasive species Cirsium arvense and Stachys byzanthina in Vazroud rangelands of Iran. For optimizing results, the Cos (t) model was used for atmospheric correction on the image. Then some false bands such as NDVI, PCA, MNF and Tasselled Cap were applied on data. Supervised algorithms using maximum likelihood, minimum distance of mean and parallelepiped were used as classification techniques for evaluation against ground truth map. The results indicated that maximum likelihood maps than maps if other algorithms and B3, B4, NDVI combination than other band combinations were the most suitable for discriminate these species.