R Libraries for Remote Sensing Data Classification by K-Means Clustering and NDVI Computation in Congo River Basin, DRC

In this paper, an image analysis framework is formulated for Landsat-8 Operational Land Imager and Thermal Infrared Sensor (OLI/TIRS) scenes using the R programming language. The libraries of are shown to be effective in remote sensing data processing tasks, such as classification k-means clustering computing Normalized Difference Vegetation Index (NDVI). processed integration RStoolbox, terra, raster, rgdal auxiliary packages R. proposed approach designed exploit parameters bands cues detect land cover types vegetation corresponding spectral reflectance objects represented on Earth’s surface. Our method at time series images taken various periods monitor landscape dynamics middle part Congo River basin, Democratic Republic (DRC). Whereas previous approaches primarily used Geographic Information System (GIS) software, we explicitly use scripting methods satellite by applying extended functionality application scripts geospatial robust compared with traditional due its high automation machine-based graphical processing. algorithms adjusted spatial operations, projections transformations, object topology, map algebra. include OLI-TIRS covering three regions along river, Bumba, Basoko Kisangani, years 2013, 2015 2022. We also validate performance handling cartographic visualization visualising changes calculation NDVI analysis.