Mapping of vegetation cover in the Quillcay sub-basin (Ancash - Peru) with the Decision Tree classifier.
DOI:
https://doi.org/10.32911/as.2021.v14.n1.761Keywords:
Key words: remote sensing; vegetation cover; decision tree; Quillcay sub-basin.Abstract
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.
Downloads
References
Adauto, M. y Bram, W. 2015. «Identificación de Humedales Alto Andinos Integrando Imágenes Landsat y Aster Gdem Con Árbol de Decisión Sobre La Cabecera de Las Cuencas Pisco y Pampas En Huancavelica - Perú». XVII Simpósio Brasileiro de Sensoriamento Remoto - SBSR, 1, 29–36.
Berhane, Tedros y otros. 2018. «Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory». Remote Sensing 10 (4), 2-26.
Borràs, J.; Delegido, J.; Pezzola, A.; Pereira, M.; Morassi, G. y Camps-Valls, G. 2017. «Clasificación de Usos Del Suelo a Partir de Imágenes Sentinel-2». Revista de Teledeteccion (48), 55–66.
Colditz, René. 2015. «An Evaluation of Different Training Sample Allocation Schemes for Discrete and Continuous Land Cover Classification Using Decision Tree-Based Algorithms». Remote Sensing 7 (8), 9655–9681.
Huang, C.; Davis, L. y Townshend, J. 2002. «An Assessment of Support Vector Machines for Land Cover Classification». International Journal of Remote Sensing 23 (4), 725–49.
Keshtkar, H. y Winfried, V. 2016. «Potential Impacts of Climate and Landscape Fragmentation Changes on Plant Distributions: Coupling Multi-Temporal Satellite Imagery with GIS-Based Cellular Automata Model». Ecological Informatics 32, 145–55.
Khatami, R.; Giorgos, M., y Stehman, S. 2016. «A Meta-Analysis of Remote Sensing Research on Supervised Pixel-Based Land-Cover Image Classification Processes: General Guidelines for Practitioners and Future Research» Remote Sensing of Environment 10 (154), 89–100.
Landis, R. y Koch, G. 1977. «An Application of Hierarchical Kappa-Type Statistics in the Assessment of Majority Agreement among Multiple Observers». Biometrics 33 (2), 363–74.
MINAM. 2014. Protocolo: Análisis de Las Dinamicas de Cambio de Cobertura de La Tierra En La Comunidad Andina. Documento público. Ministerio de Ambiente.
MINAM. 2015. Mapa Nacional de Cobertura Vegetal. Ministerio del Ambiente Direccion General de Ordenamiento Territorial Ambiental.
Minnaert, M. 1941. «The Reciprocity Principle in Lunar Photometry». The Astrophysical Journal 93.
Mora, André y otros. 2017. «Land Cover Classification from Multispectral Data Using Computational Intelligence Tools: A Comparative Study». Information (Switzerland) 8 (4), 2-15
Ramana, K. y Rajesh, P. 2019. «Land Use Land Cover Classification Using a Novel Decision Tree Algorithm and Satellite Data Sets». Advances in Intelligent Systems and Computing 862, 381-389.
Ramos, V. y Ramirez, J. 2014. Análisis Multitemporal de La Cobertura Vegetal En La Microcuenca Quillcayhuanca, Periodo 1962 - 2013, Huaraz - Ancash. Tesis de pregrado. Universidad Nacional Santiago Antúnez de Mayolo. Huaraz, Perú.
Shih, H.; Douglas, A. y Hsin, T. 2019. «Guidance on and Comparison of Machine Learning Classifiers for Landsat-Based Land Cover and Land Use Mapping» International Journal of Remote Sensing 40 (4), 1248–74.
Shukla, Gaurav y otros. 2018. «Using Multi-Source Data and Decision Tree Classification in Mapping Vegetation Diversity». Spatial Information Research. 26 (5), 573–85.
USGS. 2019. Landsat 8 ( L8 ) Data Users Handbook. USA. Vaughn Ihlen. 5th ed. Vol. 5.
Yang, Chao y otros. 2017. «Improving Land Use/Land Cover Classification by Integrating Pixel Unmixing and Decision Tree Methods». Remote Sensing 9 (12), 2-16.
