LAND USE AND LAND COVER MAPPING FOR THE MEKONG RIVER DELTA REGION USING LANDSAT-8 SATELLITE IMAGES

Abstract

Land-use/land-cover maps provide fundamental information to support management activities of natural resources and environmental problems. Landsat-8 satellite provides valuable spectral data for deriving accurate regional land-use/land-cover maps. This study demonstrated an approach for mapping land-use/land-cover by combining Landsat-8 images with a high-quality reference dataset in a classification model using the Support Vector Machine algorithm. A spatial explicit land-use/land-cover map at a spatial resolution of 30 m was created for Vietnam’s Mekong River Delta (approximately 4.0 million ha). The resulted map obtained an overall accuracy of 80.7%. Though paddy rice is the dominant land-use/land-cover type (covering nearly 1.9 million ha), aquaculture farms (including rice/mangroves-aquaculture) cover a large part of the region (about 784.4 thousand ha). Results from this study provide decision-makers with a comprehensive picture of current land-use/land-cover and facilitate better adjustments to future development plans in the Mekong River Delta. The mapping methods used in this study can be replicated in other regions.