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

  • 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

Standard

Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach. / Bispo, Polyanna Da Conceição; Rodríguez-veiga, Pedro; Zimbres, Barbara; Do Couto De Miranda, Sabrina; Henrique Giusti Cezare, Cassio; Fleming, Sam; Baldacchino, Francesca; Louis, Valentin; Rains, Dominik; Garcia, Mariano; Del Bon Espírito-santo, Fernando; Roitman, Iris; Pacheco-pascagaza, Ana María; Gou, Yaqing; Roberts, John; Barrett, Kirsten; Ferreira, Laerte Guimaraes; Shimbo, Julia Zanin; Alencar, Ane; Bustamante, Mercedes; Woodhouse, Iain Hector; Eyji Sano, Edson; Ometto, Jean Pierre; Tansey, Kevin; Balzter, Heiko.

In: Remote Sensing, Vol. 12, No. 17, 19.08.2020, p. 2685.

Research output: Contribution to journalArticlepeer-review

Harvard

Bispo, PDC, Rodríguez-veiga, P, Zimbres, B, Do Couto De Miranda, S, Henrique Giusti Cezare, C, Fleming, S, Baldacchino, F, Louis, V, Rains, D, Garcia, M, Del Bon Espírito-santo, F, Roitman, I, Pacheco-pascagaza, AM, Gou, Y, Roberts, J, Barrett, K, Ferreira, LG, Shimbo, JZ, Alencar, A, Bustamante, M, Woodhouse, IH, Eyji Sano, E, Ometto, JP, Tansey, K & Balzter, H 2020, 'Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach', Remote Sensing, vol. 12, no. 17, pp. 2685. https://doi.org/10.3390/rs12172685

APA

Bispo, P. D. C., Rodríguez-veiga, P., Zimbres, B., Do Couto De Miranda, S., Henrique Giusti Cezare, C., Fleming, S., Baldacchino, F., Louis, V., Rains, D., Garcia, M., Del Bon Espírito-santo, F., Roitman, I., Pacheco-pascagaza, A. M., Gou, Y., Roberts, J., Barrett, K., Ferreira, L. G., Shimbo, J. Z., Alencar, A., ... Balzter, H. (2020). Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach. Remote Sensing, 12(17), 2685. https://doi.org/10.3390/rs12172685

Vancouver

Bispo PDC, Rodríguez-veiga P, Zimbres B, Do Couto De Miranda S, Henrique Giusti Cezare C, Fleming S et al. Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach. Remote Sensing. 2020 Aug 19;12(17):2685. https://doi.org/10.3390/rs12172685

Author

Bispo, Polyanna Da Conceição ; Rodríguez-veiga, Pedro ; Zimbres, Barbara ; Do Couto De Miranda, Sabrina ; Henrique Giusti Cezare, Cassio ; Fleming, Sam ; Baldacchino, Francesca ; Louis, Valentin ; Rains, Dominik ; Garcia, Mariano ; Del Bon Espírito-santo, Fernando ; Roitman, Iris ; Pacheco-pascagaza, Ana María ; Gou, Yaqing ; Roberts, John ; Barrett, Kirsten ; Ferreira, Laerte Guimaraes ; Shimbo, Julia Zanin ; Alencar, Ane ; Bustamante, Mercedes ; Woodhouse, Iain Hector ; Eyji Sano, Edson ; Ometto, Jean Pierre ; Tansey, Kevin ; Balzter, Heiko. / Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach. In: Remote Sensing. 2020 ; Vol. 12, No. 17. pp. 2685.

Bibtex

@article{e5391e79b8a74e6790a33bb7452dd167,
title = "Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach",
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.",
author = "Bispo, {Polyanna Da Concei{\c c}{\~a}o} and Pedro Rodr{\'i}guez-veiga and Barbara Zimbres and {Do Couto De Miranda}, Sabrina and {Henrique Giusti Cezare}, Cassio and Sam Fleming and Francesca Baldacchino and Valentin Louis and Dominik Rains and Mariano Garcia and {Del Bon Esp{\'i}rito-santo}, Fernando and Iris Roitman and Pacheco-pascagaza, {Ana Mar{\'i}a} and Yaqing Gou and John Roberts and Kirsten Barrett and Ferreira, {Laerte Guimaraes} and Shimbo, {Julia Zanin} and Ane Alencar and Mercedes Bustamante and Woodhouse, {Iain Hector} and {Eyji Sano}, Edson and Ometto, {Jean Pierre} and Kevin Tansey and Heiko Balzter",
year = "2020",
month = aug,
day = "19",
doi = "10.3390/rs12172685",
language = "English",
volume = "12",
pages = "2685",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI",
number = "17",

}

RIS

TY - JOUR

T1 - Woody Aboveground Biomass Mapping of the Brazilian Savanna with a Multi-Sensor and Machine Learning Approach

AU - Bispo, Polyanna Da Conceição

AU - Rodríguez-veiga, Pedro

AU - Zimbres, Barbara

AU - Do Couto De Miranda, Sabrina

AU - Henrique Giusti Cezare, Cassio

AU - Fleming, Sam

AU - Baldacchino, Francesca

AU - Louis, Valentin

AU - Rains, Dominik

AU - Garcia, Mariano

AU - Del Bon Espírito-santo, Fernando

AU - Roitman, Iris

AU - Pacheco-pascagaza, Ana María

AU - Gou, Yaqing

AU - Roberts, John

AU - Barrett, Kirsten

AU - Ferreira, Laerte Guimaraes

AU - Shimbo, Julia Zanin

AU - Alencar, Ane

AU - Bustamante, Mercedes

AU - Woodhouse, Iain Hector

AU - Eyji Sano, Edson

AU - Ometto, Jean Pierre

AU - Tansey, Kevin

AU - Balzter, Heiko

PY - 2020/8/19

Y1 - 2020/8/19

N2 - 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.

AB - 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.

U2 - 10.3390/rs12172685

DO - 10.3390/rs12172685

M3 - Article

VL - 12

SP - 2685

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 17

ER -