Assessment of sources and distribution of sand dunes near Baiji City - Iraq using remote sensing techniques


The production of thematic maps, such as those depicting land cover, using an image classification is one of the most common applications of remote sensing. Several methods exist for remote sensing image classification; they include supervised, unsupervised and other approaches. Accuracy assessment of a remote sensing output is a most important step in classification of remotely sensed data, and without accuracy assessment the quality of map or output produced would be of lesser value to the end user. This paper perform supervised classification technique on remote sensing data for land cover classification in Baiji area and evaluate the accuracy result of classification technique using ERDAS IMAGINE V9.2. The study used Landsat 7 satellite image ETM+ as a primary data, with spatial resolution 30 m x 30 m. The land cover classes for the study area were classified into five themes. A total of 96 sample points were collected using Random Sampling. The results showed that the overall accuracy for the supervised classification was 91.67%, where Kappa statistics was 0.8757.