Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach

Research output: Contribution to journalArticlepeer-review

  • External authors:
  • Pedro Rodríguez-veiga
  • Barbara Zimbres
  • Sabrina Do Couto De Miranda
  • Cassio Henrique Giusti Cezare
  • Sam Fleming
  • Francesca Baldacchino
  • Valentin Louis
  • Dominik Rains
  • Mariano Garcia
  • Fernando Del Bon Espírito-santo
  • Iris Roitman
  • Ana María Pacheco-pascagaza
  • Yaqing Gou
  • John Roberts
  • Kirsten Barrett
  • Laerte Guimaraes Ferreira
  • Julia Zanin Shimbo
  • Ane Alencar
  • Mercedes Bustamante
  • Iain Hector Woodhouse
  • Edson Eyji Sano
  • Jean Pierre Ometto
  • Kevin Tansey
  • Heiko Balzter

Abstract

The tropical savanna in Brazil known as the Cerrado covers circa 23% of the Brazilian territory, but only 3% of this area is protected. High rates of deforestation and degradation in the woodland and forest areas have made the Cerrado the second-largest source of carbon emissions in Brazil. However, data on these emissions are highly uncertain because of the spatial and temporal variability of the aboveground biomass (AGB) in this biome. Remote-sensing data combined with local vegetation inventories provide the means to quantify the AGB at large scales. Here, we quantify the spatial distribution of woody AGB in the Rio Vermelho watershed, located in the centre of the Cerrado, at a high spatial resolution of 30 metres, with a random forest (RF) machine-learning approach. We produced the first high-resolution map of the AGB for a region in the Brazilian Cerrado using a combination of vegetation inventory plots, airborne light detection and ranging (LiDAR) data, and multispectral and radar satellite images (Landsat 8 and ALOS-2/PALSAR-2). A combination of random forest (RF) models and jackknife analyses enabled us to select the best remote-sensing variables to quantify the AGB on a large scale. Overall, the relationship between the ground data from vegetation inventories and remote-sensing variables was strong (R2 = 0.89), with a root-mean-square error (RMSE) of 7.58 Mg ha−1 and a bias of 0.43 Mg ha−1.

Bibliographical metadata

Original languageEnglish
Pages (from-to)2685
JournalRemote Sensing
Volume12
Issue number17
DOIs
Publication statusPublished - 19 Aug 2020