Enhanced Vegetation Cover Assessment Using Sentinel-2A: A Unified Perspective on NDVI, SAVI, and GNDVI
摘要
This study uses Sentinel-2A multispectral imagery to provide a thorough analysis of the vegetation cover in the Sillod area of the Aurangabad District, Maharashtra. In order to distinguish between different vegetation types, such as sparse, moderate, and dense vegetation, our research focuses on the computation of well-known vegetation indices, such as NDVI, SAVI, and GNDVI. By using a semiautomatic object-based classification method, we were able to identify features with excellent results. The accuracy assessment of the study yielded encouraging results. The NDVI demonstrated a remarkable 90.69% overall accuracy, with SAVI and GNDVI following closely behind at 83.58% and 93.23%, respectively. These results highlight the NDVI and GNDVI's potential usefulness for extracting vegetation in our study area. It illustrates how important it is to use Sentinel-2A imagery and sophisticated spectral indices for accurate vegetation analysis in Sillod, Maharashtra's changing landscape.