For the actual classification and generation of forest maps, a supervised statistical maximum
likelihood classification (MLC) has been used assuming that the training samples have the
Gaussian distribution (Richards and Xia 1999). In order to define the sites for the training
signature selection, from the images, two to three areas of interest (AOI) representing the forest
and non-forest classes have been selected through thorough analysis using a polygon-based
approach. The separability of the training signatures was firstly checked in feature space and
then evaluated using transformed-divergence (TD) separability measure. The values of TD
separability measure range from 0 to 2.0 and indicate how well the selected pairs are statistically
separate. The values greater than 1.9 indicate that the pairs have good separability (ENVI 1999). After the investigation, the samples that demonstrated the greatest separability were chosen to
form the final signatures. The final signatures included about 568-784 pixels. Looking at the
classified images, one can observe what kind of changes had occurred in those periods in the
forest cover of the Bogdkhan Mountain. The available forest map, the satellite images and the
results of the MLC are shown in figure 1