The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 953–960, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-953-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 953–960, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-953-2020

  21 Aug 2020

21 Aug 2020

COMBINING ENVIRONMENTAL AND LANDSAT ANALYSIS READY DATA FOR VEGETATION MAPPING: A CASE STUDY IN THE BRAZILIAN SAVANNA BIOME

H. N. Bendini1, L. M. G. Fonseca1, M. Schwieder2, P. Rufin2, T. S. Korting1, A. Koumrouyan1, and P. Hostert2,3 H. N. Bendini et al.
  • 1INPE, National Institute for Space Research, Sao Jose dos Campos, Brazil
  • 2Geography Department, Humboldt-Universität zu Berlin, Berlin, Germany
  • 3IRI THESys, Integrative Research Institute on Transformations of Human-Environment Systems, Berlin, Germany

Keywords: Vegetation mapping, Cerrado, Phenology, Data mining, Random Forest

Abstract. The Cerrado biome in Brazil covers approximately 24% of the country. It is one of the richest and most diverse savannas in the world, with 23 vegetation types (physiognomies) consisting mostly of tropical savannas, grasslands, forests and dry forests. It is considered as one of the global hotspots of biodiversity because of the high level of endemism and rapid loss of its original habitat. This work aims to analyze the potential of Landsat Analysis Ready Data (ARD) in combination with different environmental data to classify the vegetation in the Cerrado in two different hierarchical levels. Here we present results of a pixel-based modelling exercise, in which field data were combined with a set of input variables using a Random Forest classification approach. On the first hierarchical level, with the three classes savanna, grasslands and forest, our model results reached f1-scores of 0.86, 0.87 and 0.85 leading to an overall accuracy of 0.86. In the second hierarchical level we differentiated a total of 12 vegetation physiognomies with an overall accuracy of 0.77.