Mapping Floristic Composition Using Sentinel-2A in Sagalla, Kenya (2022)

The quantification of vegetation structure and composition at local and global scales provides valuable information for understanding the balance of the natural and human-made environment, which is crucial for natural resource planning and management, and the sustenance of ecosystem biodiversity. In this study, we proposed using the Sentinel 2A imagery to classify vegetation cover into communities based on the floristic association of individual vegetation species. We apply traditional remote sensing techniques to process the satellite image and identify training regions of interest (ROI) which are thoroughly assessed for spectral uniqueness before using the pixel-based supervised classification algorithms for our classification. Ground truthing assessment and species dominance computations are done to determine the vegetation community composition and naming based on floristic associations. We apply the floristic compositions output in analysing elephant movement tracks in the area, to assess the potential influence the location of specific vegetation species and communities utilized by elephants has on their movement and presence, as well as on elephant bulls and family groupings. The results show that the 10 m spatial resolution Sentinel-2A is suitable for investigating and mapping vegetation species in communities for large-scale mapping operations. We determined Near-Infrared band 8 and shortwave Infrared band 11 as key for identifying and differentiating ROIs at the floristic association community vegetation mapping level. We attained an overall accuracy of 87.395%. The analysis proved the 10 m spatial resolution of Sentinel 2A to be sufficient in distinguishing vegetation communities, including those with similar dominant species but variations in other contributing species. We also found a direct connection between vegetation location and elephant movement based on the summative analysis of utilised vegetation by the different elephant groupings. Bull elephants were predominantly present in areas with Combretum, family groups in areas with Commiphora, and mixed groups with both bulls and families in areas with Commiphora, and Cissus. This study shows the value that remote-sensing scientific support can offer conservationists and governments in objective evidence-based land management, policy making and governance.