Delineation of terrain features in Demini’s Watershed – Setentrional Amazonia using regional geomorphometry

The mapping of terrain features relies on the necessity an object-based approach, which can be related to constitution units. regionalization land surface parameters enables assessment characteristics inside unities and enhances heterogeneity outside these patches. This study presents a classification methodology for hierarchical geomorphometric delineation, using visual Random Forest (RF) in regionalized dataset variables, applied Demini’s watershed, north Amazonia. These calculated by segments derived from multiresolution segmentation, were evaluated order identify had major contributions RF’s classifications. characterization great correspondence with Environmental Informations Database (BDIA) data geomorphological mapping, used as reference this work. Overall Accuracy RF taxon 1 was 96%, while Taxon 2 Highland Lowland models reached 84% 87%, respectively. Identification subdomain classes possible mostly digital elevation model (DEM) variables directly DEM. delineation floodplain presented significant differences between results, including BDIA’s data.