Burned area detection based on time-series analysis in a cloud computing environment

J. A. Anaya, W. F. Sione, A. M. Rodríguez-Montellano

Resultado de la investigación: Contribución a una revistaArtículoInvestigaciónrevisión exhaustiva

Resumen

© 2018, Universitat Politecnica de Valencia. All rights reserved. There are large omission errors in the estimation of burned area in map products that are generated at a global scale. This error is then inherited by other models, for instance, those used to report Greenhouse Gas Emissions using a “bottom up” approach. This study evaluates temporal methods to improve burned area detection using Landsat 5-TM and 8-OLI. In this process, the normalized burn ratio (NBR) was used to highlight burned areas and thresholds to classify burned and non-burned areas. In order to maximize the burned area detection two alternatives to the temporal dNBR method were evaluated: the relative form of the temporal difference RdNBR and the use of time series metrics. The processing, algorithm development and access to Landsat data was made on the Google Earth Engine GEE platform. Three regions of Latin America with large fire occurrence were selected: The Amazon Forest in Colombia, the transition from Chiquitano to Amazon Forest in Bolivia, and El Chaco Region in Argentina. The accuracy assessment of these new products was based on burned area protocols. The best model classified 85% of burned areas in the Chiquitano Forests of Bolivia, 63% of the burned areas of the Amazon Forests of Colombia and 69% of burned areas in El Chaco of Argentina.
IdiomaInglés estadounidense
Páginas61-73
Número de páginas13
PublicaciónRevista de Teledeteccion
DOI
EstadoPublicada - 1 ene 2018

Huella dactilar

time series analysis
Landsat
bottom-up approach
accuracy assessment
Bolivia
Colombia
engine
Argentina
greenhouse gas
time series
detection
search engine
Latin America
product
method

Citar esto

@article{15983e8b126f43998e36fe8d080d88f9,
title = "Burned area detection based on time-series analysis in a cloud computing environment",
abstract = "{\circledC} 2018, Universitat Politecnica de Valencia. All rights reserved. There are large omission errors in the estimation of burned area in map products that are generated at a global scale. This error is then inherited by other models, for instance, those used to report Greenhouse Gas Emissions using a “bottom up” approach. This study evaluates temporal methods to improve burned area detection using Landsat 5-TM and 8-OLI. In this process, the normalized burn ratio (NBR) was used to highlight burned areas and thresholds to classify burned and non-burned areas. In order to maximize the burned area detection two alternatives to the temporal dNBR method were evaluated: the relative form of the temporal difference RdNBR and the use of time series metrics. The processing, algorithm development and access to Landsat data was made on the Google Earth Engine GEE platform. Three regions of Latin America with large fire occurrence were selected: The Amazon Forest in Colombia, the transition from Chiquitano to Amazon Forest in Bolivia, and El Chaco Region in Argentina. The accuracy assessment of these new products was based on burned area protocols. The best model classified 85{\%} of burned areas in the Chiquitano Forests of Bolivia, 63{\%} of the burned areas of the Amazon Forests of Colombia and 69{\%} of burned areas in El Chaco of Argentina.",
author = "Anaya, {J. A.} and Sione, {W. F.} and Rodr{\'i}guez-Montellano, {A. M.}",
year = "2018",
month = "1",
day = "1",
doi = "10.4995/raet.2018.8618",
language = "American English",
pages = "61--73",
journal = "Revista de Teledeteccion",
issn = "1133-0953",
publisher = "Asociacion Espanola de Teledeteccion",

}

Burned area detection based on time-series analysis in a cloud computing environment. / Anaya, J. A.; Sione, W. F.; Rodríguez-Montellano, A. M.

En: Revista de Teledeteccion, 01.01.2018, p. 61-73.

Resultado de la investigación: Contribución a una revistaArtículoInvestigaciónrevisión exhaustiva

TY - JOUR

T1 - Burned area detection based on time-series analysis in a cloud computing environment

AU - Anaya, J. A.

AU - Sione, W. F.

AU - Rodríguez-Montellano, A. M.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - © 2018, Universitat Politecnica de Valencia. All rights reserved. There are large omission errors in the estimation of burned area in map products that are generated at a global scale. This error is then inherited by other models, for instance, those used to report Greenhouse Gas Emissions using a “bottom up” approach. This study evaluates temporal methods to improve burned area detection using Landsat 5-TM and 8-OLI. In this process, the normalized burn ratio (NBR) was used to highlight burned areas and thresholds to classify burned and non-burned areas. In order to maximize the burned area detection two alternatives to the temporal dNBR method were evaluated: the relative form of the temporal difference RdNBR and the use of time series metrics. The processing, algorithm development and access to Landsat data was made on the Google Earth Engine GEE platform. Three regions of Latin America with large fire occurrence were selected: The Amazon Forest in Colombia, the transition from Chiquitano to Amazon Forest in Bolivia, and El Chaco Region in Argentina. The accuracy assessment of these new products was based on burned area protocols. The best model classified 85% of burned areas in the Chiquitano Forests of Bolivia, 63% of the burned areas of the Amazon Forests of Colombia and 69% of burned areas in El Chaco of Argentina.

AB - © 2018, Universitat Politecnica de Valencia. All rights reserved. There are large omission errors in the estimation of burned area in map products that are generated at a global scale. This error is then inherited by other models, for instance, those used to report Greenhouse Gas Emissions using a “bottom up” approach. This study evaluates temporal methods to improve burned area detection using Landsat 5-TM and 8-OLI. In this process, the normalized burn ratio (NBR) was used to highlight burned areas and thresholds to classify burned and non-burned areas. In order to maximize the burned area detection two alternatives to the temporal dNBR method were evaluated: the relative form of the temporal difference RdNBR and the use of time series metrics. The processing, algorithm development and access to Landsat data was made on the Google Earth Engine GEE platform. Three regions of Latin America with large fire occurrence were selected: The Amazon Forest in Colombia, the transition from Chiquitano to Amazon Forest in Bolivia, and El Chaco Region in Argentina. The accuracy assessment of these new products was based on burned area protocols. The best model classified 85% of burned areas in the Chiquitano Forests of Bolivia, 63% of the burned areas of the Amazon Forests of Colombia and 69% of burned areas in El Chaco of Argentina.

U2 - 10.4995/raet.2018.8618

DO - 10.4995/raet.2018.8618

M3 - Article

SP - 61

EP - 73

JO - Revista de Teledeteccion

T2 - Revista de Teledeteccion

JF - Revista de Teledeteccion

SN - 1133-0953

ER -