Figure
5. Output graph of the decision tree analysis. The contents in each box
are: top part is the classification criterion; gini denotes Gini
coefficient; samples denote the total number of samples for
classification―189 in the box at the 1st stage means 70% of the total
samples (270), which is used as learning data; value denotes the number
of samples, from left to right, Grassland, Forest, and Wetland
(Mari ); class denotes the greatest share of classified samples.
Box colors (orange, green, and purple) corresponds with the class
(wetland, forest, and grassland).
The decision-tree’s classification model was extrapolated for the Tyrma
region, and the produced landcover map is shown in Figure 6. Comparing
this map with the terrain map (Figure 1b), we can see that wetland
(Mari ) covers in the valley areas widely. Across the five large
river basins, wetland is particularly distributed in the Gujik River
Basin. Grassland also seems to cover some of the valley areas, but the
area of grassland is apparently smaller than that of wetland. Mountain
slopes, the areas from valley edge to ridge, were mostly covered with
forest.