LAND USE / LAND COVER MAPPING FROM SENTINEL 2 DATA USING MACHINE LEARNING ALGORITHMS

Abstract

Land cover/land use (LULC) have an important impact on land degradation,erosion and water availability therefore mapping of patterns and spatial distribution ofLULC is essential for land management. Accurate mapping of complex land cover andland use classes using remotely sensed data requires robust classification methods.Various classification algorithms and satellite images have been used in recent years. Forthis study, moderate resolution Sentinel-2 image was used. In order to evaluate thepotential of the input image and derive land cover map in complex urban area of BanjaLuka, Republic of Srpska with highest possible precision, two machine learningalgorithms where applied: Supported Vector Machines (SVM) and Random Forst (RF).An overall classification accuracy of 90,82% with kappa value of 0,87 and 88,29 withkappa value of 0,84 was achieved using SVM and RF. The study showed that ofmachine learning algorithms on Sentinel-2 imagery can results in accurate land covermaps.