Application of Sentinel-2A/B and Landsat 9 Imagery in Vegetation Cover Assessment: A Case Study in Dak Glong and Krong No Districts, Dak Nong Province

Abstract This study evaluates vegetation cover in Dak Glong and Krong No districts using Sentinel-2 and Landsat 9 satellite imagery, employing a robust methodological framework. The research utilizes Support Vector Machine (SVM) classification within the Google Earth Engine (GEE) platform, ensuring efficient and accurate land use and land cover (LULC) mapping. To assess classification accuracy, the study applies Kappa coefficient and overall accuracy metrics, comparing the performance of both satellite systems. The results indicate that Sentinel-2 imagery provides superior classification accuracy, particularly in distinguishing evergreen forests, semi-evergreen forests, and agricultural land, attributed to its finer spatial resolution. Sentinel-2 achieved an overall accuracy of 85.56% (Kappa = 0.82), while Landsat 9 obtained 83.33% (Kappa = 0.80). These findings highlight the advantages of Sentinel-2 for high-precision vegetation monitoring and reinforce its suitability for environmental assessment. The study contributes to improving remote sensing methodologies for land resource management and environmental monitoring, supporting sustainable development initiatives.