EVALUATION OF THE PERFORMANCE OF SPECTRAL INDICES FOR BURNED AREA DETECTION IN THE MUNICIPALITY OF UBERABA (MG)
DOI:
https://doi.org/10.14393/BGJ-v16n3-a2025-79274Keywords:
Remote sensing, Cerrado, Google Earth EngineAbstract
The high recurrence of wildfires in the Cerrado biome, associated with climate change and intensive agricultural practices, has caused severe impacts on biodiversity and ecosystem services. The use of spectral indices derived from satellite imagery has proven effective in identifying burn areas, although it still presents limitations in agricultural regions. This study aimed to evaluate the performance of different spectral indices in detecting fire scars in the municipality of Uberaba (MG), Brazil. Images from the Sentinel-2A sensor were used, obtained via the Google Earth Engine (GEE) platform, covering periods before and after the fire events recorded in 2022. Five indices were analyzed: Normalized Burn Ratio (NBR), Normalized Burn Ratio-SWIR (NBRSWIR), Normalized Difference Shortwave Infrared Index (NDSWIR), Mid-Infrared Bi-Spectral Index (MIRBI), and Normalized Burn Ratio Plus (NBR+). Classification accuracy was assessed based on comparison with a reference map, using the Random Forest algorithm. The NBRSWIR and MIRBI indices showed the best performance, with the former standing out in producer accuracy and the latter in user accuracy, indicating, respectively, greater ability to effectively detect burned areas and lower occurrence of false positives. The combination of Sentinel-2A bands 11 and 12 was crucial for improving the classification results, highlighting the relevance of the shortwave infrared region in identifying burned areas in landscapes dominated by agricultural crops. These findings reinforce the potential of shortwave infrared-based indices for wildfire monitoring in anthropized regions of the Cerrado.
References
ALCARAS, E.; CONSTANTINO, D.; GUASTAFERRO, F.; PARENTE, C.; PEPE, M. Normalized Burn Ratio Plus (NBR+): a new index for Sentinel-2 imagery. Remote Sensing, v. 14, 2022, p. 1727. DOI: https://doi.org/10.3390/rs14071727
ALMEIDA, T. S.; CALIJURI, M. L.; PINTO, L. B. Zoneamento agro-climático da cana-de-açúcar para o estado de Minas Gerais com base em regressões múltiplas. Revista Brasileira de Meteorologia, v. 28, 2013, p. 352-355. DOI: https://doi.org/10.1590/S0102-77862013000300011
ARRUDA, V. L. S.; PIONTEKOWSKI, V. J.; ALENCAR, A.; PEREIRA, R. S.; MATRICARDI, E. A. T. An alternative approach for mapping burn scars using Landsat imagery, Google Earth Engine, and Deep Learning in the Brazilian Savanna. Remote Sensing Applications: Society and Environment, v. 22, 2012, p. 100472. DOI: https://doi.org/10.1016/j.rsase.2021.100472
ASTOLA, H.; HÄME, T.; SIRRO, L.; MOLINIER, M.; KILPI, J. Comparison of Sentinel-2 and Landsat 8 imagery for forest variable prediction in boreal region. Remote Sensing of Environment, v. 223, 2019, p. 257-273. DOI: https://doi.org/10.1016/j.rse.2019.01.019
BA, R.; SONG, W.; LI, X.; XIE, Z.; LO, S. Integration of multiple spectral indices and a neural network for burned area mapping based on MODIS data. Remote Sensing, v. 11, 2019, p. 326. DOI: https://doi.org/10.3390/rs11030326
BOSCHETTI, L.; ROY, D. P.; GIGLIO, L.; HUANG, H.; ZUBKOVA, M.; HUMBER, M. L. Global validation of the collection 6 MODIS burned area product. Remote Sensing of Environment, v. 235, 2019, p. 111490. DOI: https://doi.org/10.1016/j.rse.2019.111490
BRASIL. Presidência da República, Casa Civil, Subchefia para Assuntos Jurídicos, n° 12.651, de 25 de maio de 2012. Dispõe sobre a proteção da vegetação nativa; altera as Leis nºs 6.938, de 31 de agosto de 1981, 9.393, de 19 de dezembro de 1996, e 11.428, de 22 de dezembro de 2006; revoga as Leis nºs 4.771, de 15 de setembro de 1965, e 7.754, de 14 de abril de 1989, e a Medida Provisória nº 2.166-67, de 24 de agosto de 2001; e dá outras providências. Brasília, DF, 2012. Disponível em: <http://www.planalto.gov.br/ccivil_03/_ato2011-2014/2012/lei/L12651compilado.htm>. Acesso em: 11 mar. 2025. Diário Oficial da União em: 26 de maio de 2012.
BREXÓ, E. A.; MATTOS, L. M.; SUSZEK, G. Caracterização de uso e ocupação do solo na região do vale do Ivinhema-MS utilizando a plataforma Google Earth Engine. Brazilian Journal of Animal and Environmental Research, v. 6, n. 1, 2023, p. 251–263. DOI: https://doi.org/10.34188/bjaerv6n1-022
CAMPAGNOLO, M. L.; LIBONATI, R.; RODRIGUES, J. A.; PEREIRA, J. M. C. A comprehensive characterization of MODIS daily burned area mapping accuracy across fire sizes in tropical savannas. Remote Sensing of Environment, v. 252, 2021, p. 112115. DOI: https://doi.org/10.1016/j.rse.2020.112115.
CHEN, W.; MORIYA, K.; SAKAI, T.; KOYAMA, L.; CAO, C. X. Mapping a burned forest area from Landsat TM data by multiple methods. Geomatics, Natural Hazards and Risk, v. 7, 2016, p. 384-402. DOI: https://doi.org/10.1080/19475705.2014.925982
COELHO, M. H.; MORELLI, F.; BITTENCOURT, O. O.; SANTOS, R. Método para a Classificação de Áreas Queimadas Baseado em Aprendizado de Máquina Automatizado. Anais XIII Computer on the Beach - COTB’22, Itajaí, SC, 2022. p. 029-036. Disponível em: https://periodicos.univali.br/index.php/acotb/article/view/18707. Acesso em: 11 mar. 2025.
COMPANHIA NACIONAL DE ABASTECIMENTO (CONAB). Acompanhamento da safra brasileira de grãos. Safra 2021/22 – Primeiro levantamento. v. 8, 2021, p. 87. Disponível em: https://www.gov.br/inpe/pt-br/assuntos/ultimas-noticias/divulgacao-do1deg-levantamento-da-safra-de-graos-safra-2021-22-realizada-pela-conab-comparticipacao-do-inpe-mcti. Acesso em: 11 mar. 2025.
DALDEGAN, G. A.; ROBERTS, D. A.; RIBEIRO, F. D. F. Spectral mixture analysis in Google Earth Engine to model and delineate fire scars over a large extent and a long time-series in a rainforest-savanna transition zone. Remote Sensing of Environment, v. 232, 2019, p. 111340. DOI: https://doi.org/10.1016/j.rse.2019.111340
FARHADI, H.; MOKHTARZADE, M.; EBADI, H.; BEIRAMI, B. A. Rapid and automatic burned area detection using Sentinel-2 time-series images in Google Earth Engine cloud platform: a case study over the Andika and Behbahan regions, Iran. Environmental Monitoring and Assessment, v. 194, 2022, p. 369. DOI: https://doi.org/10.1007/s10661- 022-10045-4
FRANQUESA, A. M.; STEHMAN, S. V.; CHUVIECO, E. Assessment and characterization of sources of error impacting the accuracy of global burned area products. Remote Sensing of Environment, v. 280, 2022, p. 113214. DOI: https://doi.org/10.1016/j.rse.2022.113214
GERARD, F.; PLUMMER, S.; WADSWORTH, R.; SANFELIU, A. F.; ILIFFE, L.; BALZTER, H. Forest fire scar detection in the boreal forest with multitemporal spot-vegetation data. IEEE Transactions on Geoscience and Remote Sensing, v. 41, 2023, p. 2575-2585. DOI: https://doi.org/10.1109/TGRS.2003.819190
GIGLIO, L.; SCHROEDER, W.; JUSTICE, C. O. The collection 6 MODIS active fire detection algorithm and fire products. Remote Sensing of Environment, v. 178, 2016, p. 31-41. DOI: https://doi.org/10.1016/j.rse.2016.02.054
INSTITUTO BRASILEIRO DE GEOGRAFIA E ESTATÍSTICA (IBGE). Cidades: Uberaba. 2022. Disponível em: <https://cidades.ibge.gov.br/brasil/mg/uberaba/panorama>. Acesso em: 09 mar. 2025.
INSTITUTO NACIONAL DE PESQUISAS ESPACIAIS (INPE). Banco de Dados de Queimadas (BDQueimadas). 2021. Disponível em: http://www.inpe.br/queimadas/bdqueimadas. Acesso em: 09 mar. 2025.
KEY, C. H.; BENSON, N. Landscape assessment (LA) sampling and analysis methods. USDA Forest Service, Rocky Mountain Research Station, General Technical Report RMRS-GTR-164-CD. (Fort Collins, CO), 2006. Disponível em: https://www.fs.fed.us/rm/pubs/rmrs_gtr164/rmrs_gtr164_13_land_assess.pdf. Acesso em: 09 mar. 2025.
LANEVE, G.; DI FONZO, M.; PAMPANONI, V.; MORLES, R. B. Progress and limitations in the satellite-based estimate of burnt areas. Remote Sensing, v. 16, 2024, p. 42, 2024. DOI: https://doi.org/10.3390/rs16010042.
LIU, S.; ZHENG, Y.; DALPONTE, M.; TONG, X. A novel fire index-based burned area change detection approach using Landsat-8 OLI data. European Journal of Remote Sensing, v. 53, 2020, p. 104-112. DOI: https://doi.org/10.1080/22797254.2020.1738900
MAHDIANPARI, M.; SALEHI, B.; MOHAMMADIMANESH, F.; HOMAYOUNI, S.; GILL, E. The first wetland inventory map of Newfoundland at a spatial resolution of 10 m using Sentinel1 and Sentinel-2 data on the Google Earth Engine cloud computing platform. Remote Sensing, v. 11, 2019, p. 43. DOI: https://doi.org/10.3390/rs11010043
MAPBIOMAS. Coleção de séries de mapas de uso e cobertura do solo brasileiro. 2023. Disponível em: http://mapbiomas.org/. Acesso em: 09 mar. 2025.
MINAS GERAIS. Deliberação Normativa COPAM n. 213, de 22 de fevereiro de 2017. Diário Executivo. Regulamenta o disposto no art. 9º, inciso XIV, alínea “a” e no art. 18, § 2º da Lei Complementar Federal nº 140, de 8 de dezembro de 2011 [...]. Belo Horizonte, MG, 2017. Disponível em: https://www.siam.mg.gov.br/sla/download.pdf?idNorma=43778. Acesso em: 11 mar. 2025.
MPAKAIRI, K. S.; NDAIMANI, H.; KAVHU, B. Exploring the utility of Sentinel-2 MSI derived spectral indices in mapping burned areas in different land-cover types. Scientific African, v. 10, 2020, p. 565. DOI: https://doi.org/10.1016/j.sciaf.2020.e00565
OLIVA, P.; MARTIN, P.; CHUVIECO, E. Burned area mapping with MERIS post-fire image. International Journal of Remote Sensing, v. 32, 2011, p. 4175-4201. DOI: https://doi.org/10.1080/01431161.2010.489062
PANTALEÃO JÚNIOR, C. M.; FERREIRA, R. V. Avaliação do desempenho do índice ∆NBR para a identificação de áreas incendiadas na Microrregião de Uberaba, MG. Brazilian Geographical Journal, v. 11, n. 2, 2020, p. 159–169. DOI: https://doi.org/10.14393/BGJ-v11n2-a2020-52096
PEREA-ARDILA, M. A.; MUÑOZ, S. I.; SOPCHAK, C. H. Análise de áreas queimadas utilizando imagens Sentinel-2 no Parque Estadual do Cocó, Região Metropolitana de Fortaleza (Ceará). Revista Brasileira de Sensoriamento Remoto, v. 4, 2023, p. 067-083. DOI: https://doi.org/10.5281/zenodo.10440566
RADOUX, J.; BOGAERT, P. Good practices for object-based accuracy assessment. Remote Sensing, v. 9, 2017, p. 646. DOI: https://doi.org/10.3390/rs9070646
RIBEIRO, C. S. C.; BUCKER, P. O. M.; ALMEIDA, M. R. R.; TEIXEIRA, D. L. S. Ações antrópicas que exercem pressão sobre o Parque Nacional do Itatiaia. In: Congresso Nacional de Meio Ambiente, Poços de Caldas, MG, Brasil, 18, 2021, p. 1-12.
ROTETA, E.; BASTARRIKA, A.; PADILLA, M.; STORM, T.; CHUVIECO, E. Development of a Sentinel-2 burned area algorithm: generation of a small fire database for sub-Saharan Africa. Remote Sensing of Environment, v. 222, 2019, p. 1-17. DOI: https://doi.org/10.1016/j.rse.2018.12.011
SOUSA, H. C. de. Fogo, mudanças climáticas e a conservação da lacertofauna no Cerrado. Tese de Doutorado em Ciências do Ambiente. Universidade Federal do Tocantins. Palmas, 2023. 225p.
TEIXEIRA, A. L. S. Correlação entre índices espectrais de verdor, umidade e senescência e ocorrências de queimadas no Parque Nacional de Brasília. Dissertação de Mestrado em Geociências Aplicadas. Universidade de Brasília. 2020. 93p.
TRIGG, S.; FLASSE, S. An evaluation of different bi-spectral spaces for discriminating burned shrub-savannah. International Journal of Remote Sensing, v. 22, 2001, p. 2641-2647. DOI: https://doi.org/10.1080/01431160110053185
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Júlia Fontanesi Sousa, Dr. Renato Farias do Valle Junior, Dr. Elcides Rodrigues da Silva, Dr. Alex Garcez Utsumi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All copyrights are reserved to authors. Reproductions of any part of this journal, including the non-commercial use of figures, maps and other illustrations, are allowed provided that the original source of publication be assigned.
