Mapping of vegetation cover in the Quillcay sub-basin (Ancash - Peru) with the Decision Tree classifier.

• Autores: Santiago Bazan, Frank, Mallqui Meza, Helder, Rios Recra, Raquel
• Formato: artículo
• Fecha de Publicación: 2021
• Institución: Universidad Nacional Santiago Antúnez de Mayolo
• Repositorio: Revistas - Universidad Nacional Santiago Antunez de Mayolo
• Lenguaje: español
• OAI Identifier: oai:ojs.pkp.sfu.ca:article/761
• Enlace del recurso: http://revistas.unasam.edu.pe/index.php/Aporte_Santiaguino/article/view/761
• Nivel de acceso: acceso abierto
• Materia: Palabras clave: teledetección; cobertura vegetal; árbol de decisiones; subcuenca Quillcay.; Key words: remote sensing; vegetation cover; decision tree; Quillcay sub-basin.

The characterization and delimitation of the existing vegetation cover in a given geographic area is of vital importance for an adequate management of natural resources. In this sense, this research proposes a methodology to delimit the types of vegetation cover in the Quillcay sub-basin. The study area is located in the districts of Huaraz and Independencia, province of Huaraz, Ancash; in the middle western slope of the Cordillera Blanca and Santa river basin. The delimitation of the vegetation cover began with the identification of the dominant vegetation cover types (Andean grassland, forest, wetland and shrub thicket); then, the geographic characteristics (slope and altitude) were defined for each type of vegetation cover. Subsequently, layers were generated with the Spectral Angle Mapper (SAM) classifier and the calculation of the Normalized Difference Moisture Index (NDMI). Finally, through the decision tree classifier it was possible to integrate all the previously determined layers, thus obtaining the supervised classification with the use of Landsat 8 satellite information of 2018 and DEM Alos Palsar. The results indicate that the application of the decision tree shows an almost perfect classification accuracy with a Kappa statistic (K^) of 0.90 We consider that the proposed methodology (decision tree) is ideal for delimiting vegetation cover at subregional scale. Key words: remote sensing; vegetation cover; decision tree; Quillcay sub-basin.