Skip to main content

Table 1 Description of training ROI, validation ROI, and training pixels used for the study

From: Fusion of sentinel-1 SAR and sentinel-2 MSI data for accurate Urban land use-land cover classification in Gondar City, Ethiopia

S. N

Class name

Training ROI

Validation GCP

Training pixels

Class description

1

Built-up

40

25

2000 pixels

Urban areas with dense human-made structures, roads, etc

2

Forest

60

35

3000 pixels

Dense wooded areas with a high density of trees

3

Shrubland

35

15

1800 pixels

Areas dominated by shrubs and short trees on urban outskirts

4

Grassland

50

27

2500 pixels

Open areas covered predominantly with grass, e.g., parks

5

Water body

40

22

1800 pixels

Bodies of water, such as rivers, lakes, and reservoirs

6

Bare land

75

45

3200 pixels

Unvegetated or sparsely vegetated areas, like deserts

Total

 

300

169

14,300 pixels

Â