Members of our team participated in the groundbreaking published work to study the diversity of the Brazilian Cerrado!

The recent study is titled: "Spatial Characterization of Woody Species Diversity in Tropical Savannas Using GEDI and Optical Data".

In this study, researchers evaluated the potential of Global Ecosystem Dynamics Investigation (GEDI) data, combined with conventional satellite optical imagery and climate reanalysis data, to predict in situ alpha diversity (species richness, Simpson index, and Shannon index) among tree species. Optical data from Sentinel-2, ERA-5 climate data, SRTM-DEM, and simulated GEDI data were selected to characterize diversity in four study areas. The integration of auxiliary data proved to be effective in improving biodiversity metric predictions. Random Forest (RF) regression models were suitable for estimating tree species diversity indices from remote sensing variables.

Based on these models, we generated diversity index maps for the entire Cerrado, using all available GEDI data in orbit. For all models, the structural metric Foliage Height Diversity (FHD) was selected; the Renormalized Difference Vegetation Index (RDVI) was also chosen in all species diversity models. Our results suggest that the developed models are valuable tools for assessing species diversity in tropical savanna ecosystems, although each model can be selected based on the objectives of a specific study, the desired level of performance/error, and data availability.

Despite many opportunities for improving the predictive capabilities of the models, we believe that enhancing the development of tools and technical procedures for monitoring diversity in Brazil and worldwide is essential—an area at the forefront of knowledge.

🔗 Full paper link: https://www.mdpi.com/1424-8220/25/2/308