<![CDATA[The current remote sensing technology has produced various advantages, one of which is land cover classification. This technique is effective in land cover monitoring because of its ability to provide spatial information on the surface of the earth quickly, broadly, precisely and easily. The vegetation index obtained based on remote sensing is a fairly simple and effective method for quantitative and qualitative evaluation of cover, strength, and vegetation growth dynamics. The vegetation index using reflections from vegetation that is commonly used to evaluate vegetation quality is the normalized difference vegetation index (NDVI). Land cover classification analysis is performed with NDVI and random forest algorithms. The random forest algorithm is one of the supervised machine learning algorithms which can be used in classifying pixels in land cover classification classes. This research is aimed at classifying land cover of Sentinel-2 satellite images using NDVI and random forest algorithms. The result of this research is that the NDVI value -0.3 – 0.91 and the random forest algorithm accuracy is 91.39%, and Kappa 0.88. In conclusion, it can be said that random forest algorithms is effective to perform land cover classification by using Sentinel-2 satellite images]]>
Copyrights © 2022
