Mapping the spatial distribution of the yellowwood tree (Podocarpus henkelii) in the Weza-Ngele forest using the newly launched Sentinel-2 multispectral imager data

Abstract

ABSTRACT The conservation of indigenous tree species is not only significant for the natural heritage, but for conserving numerous species that are heavily dependent on these trees for survival. Remotely sensed data have been proven to be an effective tool for enumeration monitoring of vegetation resources. However, the utility of freely available new generation multispectral sensors with improved spatial and spectral resolutions still needs to be understood in the conservation of natural resources. Therefore, this study sought to map the spatial distribution of Podocarpus henkelii in Weza-Ngele forest using Sentinel-2 Multispectral Instrument. A total of five classes were randomly sampled and discriminated using Random Forest technique. The models created from only spectral bands were compared to those derived from combining vegetation indices and spectral bands. The Index Database was used to compute vegetation indices (VI) with 10 different VI being selected for characterizing Podocarpus land cover types. The overall accuracies of spectral bands, as well as spectral bands combined with vegetation indices, was 67% and 80%, respectively. These results underscore the utility of the new generation of multispectral sensors in successfully discriminating P.henkelii from other land cover, thus providing a cheaper and easier alternative for indigenous forest species mapping.