An Accuracy Analysis Comparison of Supervised Classification Methods for Mapping Land Cover Using Sentinel 2 Images in the Al‑Hawizeh Marsh Area, Southern Iraq

Land cover mapping of marshland areas from satellite images data is not a simple process, due to the similarity spectral characteristics land cover. This leads challenges being encountered with some covers classes, especially in wetlands classes. In this study, Sentinel 2B by ESA (European Space Agency) were used classify Al‑Hawizeh marsh/Iraq‑Iran border. Three classification methods aimed at comparing their accuracy, using multispectral spatial resolution 10 m. The process was performed three different algorithms, namely: Maximum Likelihood Classification (MLC), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). algorithms carried out ENVI 5.1 software detect six classes: deep water marsh, shallow marsh vegetation (aquatic vegetation), urban area (built‑up area), agriculture area, barren soil. results showed that MLC method applied provides higher overall accuracy kappa coefficient compared ANN SVM methods. Overall values for MLC, ANN, 85.32%, 70.64%, 77.01% respectively.