Floresta e Ambiente
https://floram.org/article/doi/10.1590/2179-8087.011518
Floresta e Ambiente
Original Article Conservation of Nature

Prediction of Burned Areas Using the Random Forest Classifier in the Minas Gerais State

Eliana Elizabet dos Santos; Nathalie Cruz Sena; Diego Balestrin; Elpidio Inácio Fernandes Filho; Liovando Marciano da Costa; Leiliane Bozzi Zeferino

Downloads: 0
Views: 3

Abstract

Abstract: Fire behavior prediction models can assist environmental agencies with fire prevention and control. This study aimed to adjust a fire prediction model for the state of Minas Gerais, Brazil. Using the R program and hotspots provided by the National Institute for Space Research (INPE) for 2010, prediction of the probability of fires through the Random Forest algorithm was conducted using the Bootstrapping method. The model generated a prediction map with global kappa value of 0.65. External validation was performed with hotspots in 2015. Results showed that 58% of the hotspots are in areas with ignition probability > 50%, being 24% of them in areas with 25-50% probability, and 17% in areas with < 25% probability. These results were considered satisfactory, demonstrating that the model is suitable for predicting fires.

Keywords

fires, modeling, environmental monitoring

References

Alves KMAS, Nóbrega RS. Uso de dados climáticos para análise espacial de risco de incêndio florestal: climatic data use for spatial analysis of forest fire risk. Mercator 2011; 10(22): 209-219. 10.4215/RM2011.1022.0013

Boadi C, Harvey SK, Gyeke-Dako A. Modelling of fire count data: fire disaster risk in Ghana. SpringerPlus 2015; 4: 794. 10.1186/s40064-015-1585-3

Bolker BM. Ecological models and Data in R. Princeton: Princeton University Press; 2008.

Boychuk D, Braun WJ, Kulperger RJ, Krougly ZL, Stanford DA. A stochastic forest fire growth model. Environmental and Ecological Statistics 2009; 16(2): 133-151. 10.1007/s10651-007-0079-z

Magalhães SR, Lima GS, Ribeiro GA. Avaliação dos incêndios florestais ocorridos no Parque Nacional da Serra da Canastra - Minas Gerais. Cerne 2012; 18(1): 135-141. 10.1590/S0104-77602012000100016

Ganteaume A, Jappiot M. What causes large fires in Southern France. Forest Ecology and Management 2013; 294: 76-85. 10.1016/j.foreco.2012.06.055

He HS, Shang BZ, Crow TR, Gustafson EJ, Shifley SR. Simulating forest fuel and fire risk dynamics across landscapes-LANDIS fuel module design. Ecological Modelling 2004; 180: 135-151.

Kobler A, Ogrinc P, Skok I, Fajfar D, Džeroski S. The final report on the results of the research project: a predictive GIS model of fire risk in the natural environment [technical report]. Ljubljana: Slovenian Forestry Institute, Jožef Stefan Institute; 2006.

Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics 1977; 33(1): 159-174. 10.2307/2529310

Lima GS. A prevenção de incêndios florestais no estado de Minas Gerais. Revista Floresta 2000; 30(1-2): 37-43. 10.5380/rf.v30i12.2364

Pereira AA, Teixeira FR, Libonati R, Melchiori EA, Carvalho LMT. Avaliação de índices espectrais para identificação de áreas queimadas no cerrado utilizando dados LandSat TM. Revista Brasileira de Cartografia 2016; 8(68): 1665-1680.

Prasad AM, Iverson LR, Liaw A. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 2006; 9(2): 181-199. 10.1007/s10021-005-0054-1

Reboita MS, Rodrigues M, Silva LF, Alves MA. Aspectos climáticos do estado de Minas Gerais (climate aspects in Minas Gerais State). Revista Brasileira de Climatologia 2015; 17: 206-226. 10.5380/abclima.v17i0.41493

Redin M, Santos GF, Miguel P, Denega GL, Lupatini M, Doneda A et al. Impactos da queima sobre atributos químicos, físicos e biológicos do solo. Ciência Florestal 2011; 21(2): 381-392. 10.5902/198050983243

Silva CHL Jr, Freire ATG, Rodrigues TCS, Viegas J, Bezerra DS. Dinâmica das queimadas na baixada maranhense. Revista de Geografia e Interdisciplinaridade 2016; 2(5): 356-375. 10.18766/2446-6549/interespaco.v2n5p355-375

Silva ED. Estudo da precipitação no estado de Minas Gerais-MG. Revista Brasileira de Climatologia 2014; 13: 120-136. 10.5380/abclima.v13i0.33345

Silva CM, Vieira JW, Neto NA, Gonçalves GL. Controle estatístico de qualidade usando o método bootstrap. Scientia Plena 2018; 14(3): 1-9. 10.14808/sci.plena.2018.037001

Souza LR, Amanajás JC, Silva APN, Braga CC, Correia MF. Determinação de padrões espaço-temporal e regiões homogêneas de precipitação pluvial no estado de Minas Gerais. Engenharia Ambiental: Pesquisa e Tecnologia 2011; 8(2): 265-280.

Valadão RC, Oliveira CV, Ker JC. Compartimentação regional do relevo e cobertura pedológica do centro-norte de Minas Gerais. Revista Geografias 2008; 1(4): 93-100.
 


Submitted date:
03/13/2018

Accepted date:
08/22/2018

5ef60c6e0e88258275e5dce5 floram Articles
Links & Downloads

FLORAM

Share this page
Page Sections