Tree cover change detection through Artificial Neural Network classification using Landsat TM and ETM+ images (case study: Golestan Province, Iran)

The aim of this research was to detect tree cover changes through Artificial Neural Network classification and post-classification comparison methods using landsat TM and ETM+ images in Golestan province, north of Iran with area of 20437.74 ha. Land uses and land covers were distinguished on the color composite image of the area and used as training sites for image classification that included all six bands of the imagery. We also used unsupervised classification to derive 100 clusters for purifying initial training sites. A post-classification comparison method was conducted on classified images of the years 1987 and 2001 and forest increase and decrease areas were identified. Accuracy assessment was implemented through test set pixels that were randomized and set aside from the training set pixels. We also used a LISS III imagery to assess the accuracy of the classification. Both methods proved the classifications and change detection in high accuracy