Abstract

Cerrado is the second largest biome of South America, with the major extension located in Brazil. This biome is considered a world biodiversity hotspot due to the rich and important biodiversity contrasting with the high threat of destruction. Monitoring using remote sensing approaches is a crucial tool for maintaining and preserving this large-scale biome. Through this context, this study compared and assessed different scenarios with Landsat 8 OLI multispectral bands and Vegetation Indices (EVI, NDVI, and SAVI) for the Cerrado mapping in Mato Grosso do Sul state, Brazil. An amount of 512 sample polygons were distributed into 2 classes: native vegetation and non-native vegetation. The Google Earth Engine platform was applied to the training and classification processes using the Random Forest method. The results showed that using Landsat 8 OLI bands obtained better results than the vegetation indices, with an overall accuracy and kappa index of 97.08% and 0.94, respectively. The mapping verified the existence of 26,80% of Cerrado original native vegetation in Mato Grosso do Sul state in 2019.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call