Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques

The semi-arid Caatinga biome is particularly susceptible to fire dynamics. Periodic droughts amplify fire risks, while anthropogenic activities such as agriculture, pasture expansion, and land-clearing significantly contribute to the prevalence of fires. This research aims to evaluate the effectiven...

Full description

Saved in:
Bibliographic Details
Main Authors: Washington J. S. Franca Rocha, Rodrigo N. Vasconcelos, Soltan Galano Duverger, Diego P. Costa, Nerivaldo A. Santos, Rafael O. Franca Rocha, Mariana M. M. de Santana, Ane A. C. Alencar, Vera L. S. Arruda, Wallace Vieira da Silva, Jefferson Ferreira-Ferreira, Mariana Oliveira, Leonardo da Silva Barbosa, Carlos Leandro Cordeiro
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Fire
Subjects:
Online Access:https://www.mdpi.com/2571-6255/7/12/437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036491588206592
author Washington J. S. Franca Rocha
Rodrigo N. Vasconcelos
Soltan Galano Duverger
Diego P. Costa
Nerivaldo A. Santos
Rafael O. Franca Rocha
Mariana M. M. de Santana
Ane A. C. Alencar
Vera L. S. Arruda
Wallace Vieira da Silva
Jefferson Ferreira-Ferreira
Mariana Oliveira
Leonardo da Silva Barbosa
Carlos Leandro Cordeiro
author_facet Washington J. S. Franca Rocha
Rodrigo N. Vasconcelos
Soltan Galano Duverger
Diego P. Costa
Nerivaldo A. Santos
Rafael O. Franca Rocha
Mariana M. M. de Santana
Ane A. C. Alencar
Vera L. S. Arruda
Wallace Vieira da Silva
Jefferson Ferreira-Ferreira
Mariana Oliveira
Leonardo da Silva Barbosa
Carlos Leandro Cordeiro
author_sort Washington J. S. Franca Rocha
collection DOAJ
description The semi-arid Caatinga biome is particularly susceptible to fire dynamics. Periodic droughts amplify fire risks, while anthropogenic activities such as agriculture, pasture expansion, and land-clearing significantly contribute to the prevalence of fires. This research aims to evaluate the effectiveness of a fire detection model and analyze the spatial and temporal patterns of burned areas, providing essential insights for fire management and prevention strategies. Utilizing deep neural network (DNN) models, we mapped burned areas across the Caatinga biome from 1985 to 2023, based on Landsat-derived annual quality mosaics and minimum NBR values. Over the 38-year period, the model classified 10.9 Mha (12.7% of the Caatinga) as burned, with an average annual burned area of approximately 0.5 Mha (0.56%). The peak burned area reached 0.89 Mha in 2021. Fire scars varied significantly, ranging from 0.18 Mha in 1985 to substantial fluctuations in subsequent years. The most affected vegetation type was savanna, with 9.8 Mha burned, while forests experienced only 0.28 Mha of burning. October emerged as the month with the highest fire activity, accounting for 7266 hectares. These findings underscore the complex interplay of climatic and anthropogenic factors, highlighting the urgent need for effective fire management strategies.
format Article
id doaj-art-ee14d6b39bc04cdebfa0bf5f3b0c7d96
institution DOAJ
issn 2571-6255
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Fire
spelling doaj-art-ee14d6b39bc04cdebfa0bf5f3b0c7d962025-08-20T02:57:07ZengMDPI AGFire2571-62552024-11-0171243710.3390/fire7120437Mapping Burned Area in the Caatinga Biome: Employing Deep Learning TechniquesWashington J. S. Franca Rocha0Rodrigo N. Vasconcelos1Soltan Galano Duverger2Diego P. Costa3Nerivaldo A. Santos4Rafael O. Franca Rocha5Mariana M. M. de Santana6Ane A. C. Alencar7Vera L. S. Arruda8Wallace Vieira da Silva9Jefferson Ferreira-Ferreira10Mariana Oliveira11Leonardo da Silva Barbosa12Carlos Leandro Cordeiro13Postgraduate Program in Earth Modeling and Environmental Sciences—PPGM, State University of Feira de Santana—UEFS, Feira de Santana 44036-900, BrazilPostgraduate Program in Earth Modeling and Environmental Sciences—PPGM, State University of Feira de Santana—UEFS, Feira de Santana 44036-900, BrazilGEODATIN–Data Intelligence and Geoinformation, Bahia Technological Park Rua Mundo, 121–Trobogy, Salvador 41301-110, BrazilPostgraduate Program in Earth Modeling and Environmental Sciences—PPGM, State University of Feira de Santana—UEFS, Feira de Santana 44036-900, BrazilPostgraduate Program in Earth Modeling and Environmental Sciences—PPGM, State University of Feira de Santana—UEFS, Feira de Santana 44036-900, BrazilPostgraduate Program in Earth Modeling and Environmental Sciences—PPGM, State University of Feira de Santana—UEFS, Feira de Santana 44036-900, BrazilForest Engineering Institute (FEI/UEAP), State University of Amapá—UEAP, Av. Pres. Getúlio Vargas, 650 Centro, Macapá 68900-070, BrazilInstituto de Pesquisa Ambiental da Amazônia (IPAM), SCN 211, Bloco B, Sala 201, Brasília 70836-520, BrazilInstituto de Pesquisa Ambiental da Amazônia (IPAM), SCN 211, Bloco B, Sala 201, Brasília 70836-520, BrazilInstituto de Pesquisa Ambiental da Amazônia (IPAM), SCN 211, Bloco B, Sala 201, Brasília 70836-520, BrazilWorld Resources Institute Brasil, Rua Cláudio Soares, 72 Cj. 1510, São Paulo 05422-030, BrazilWorld Resources Institute Brasil, Rua Cláudio Soares, 72 Cj. 1510, São Paulo 05422-030, BrazilWorld Resources Institute Brasil, Rua Cláudio Soares, 72 Cj. 1510, São Paulo 05422-030, BrazilWorld Resources Institute Brasil, Rua Cláudio Soares, 72 Cj. 1510, São Paulo 05422-030, BrazilThe semi-arid Caatinga biome is particularly susceptible to fire dynamics. Periodic droughts amplify fire risks, while anthropogenic activities such as agriculture, pasture expansion, and land-clearing significantly contribute to the prevalence of fires. This research aims to evaluate the effectiveness of a fire detection model and analyze the spatial and temporal patterns of burned areas, providing essential insights for fire management and prevention strategies. Utilizing deep neural network (DNN) models, we mapped burned areas across the Caatinga biome from 1985 to 2023, based on Landsat-derived annual quality mosaics and minimum NBR values. Over the 38-year period, the model classified 10.9 Mha (12.7% of the Caatinga) as burned, with an average annual burned area of approximately 0.5 Mha (0.56%). The peak burned area reached 0.89 Mha in 2021. Fire scars varied significantly, ranging from 0.18 Mha in 1985 to substantial fluctuations in subsequent years. The most affected vegetation type was savanna, with 9.8 Mha burned, while forests experienced only 0.28 Mha of burning. October emerged as the month with the highest fire activity, accounting for 7266 hectares. These findings underscore the complex interplay of climatic and anthropogenic factors, highlighting the urgent need for effective fire management strategies.https://www.mdpi.com/2571-6255/7/12/437forest firewildfiresemiariddrylandsburned areafire regime
spellingShingle Washington J. S. Franca Rocha
Rodrigo N. Vasconcelos
Soltan Galano Duverger
Diego P. Costa
Nerivaldo A. Santos
Rafael O. Franca Rocha
Mariana M. M. de Santana
Ane A. C. Alencar
Vera L. S. Arruda
Wallace Vieira da Silva
Jefferson Ferreira-Ferreira
Mariana Oliveira
Leonardo da Silva Barbosa
Carlos Leandro Cordeiro
Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
Fire
forest fire
wildfire
semiarid
drylands
burned area
fire regime
title Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
title_full Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
title_fullStr Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
title_full_unstemmed Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
title_short Mapping Burned Area in the Caatinga Biome: Employing Deep Learning Techniques
title_sort mapping burned area in the caatinga biome employing deep learning techniques
topic forest fire
wildfire
semiarid
drylands
burned area
fire regime
url https://www.mdpi.com/2571-6255/7/12/437
work_keys_str_mv AT washingtonjsfrancarocha mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT rodrigonvasconcelos mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT soltangalanoduverger mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT diegopcosta mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT nerivaldoasantos mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT rafaelofrancarocha mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT marianammdesantana mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT aneacalencar mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT veralsarruda mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT wallacevieiradasilva mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT jeffersonferreiraferreira mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT marianaoliveira mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT leonardodasilvabarbosa mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques
AT carlosleandrocordeiro mappingburnedareainthecaatingabiomeemployingdeeplearningtechniques