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

被引：4

作者：

dos Santos, Eliana Elizabet ^{[1
]}

Sena, Nathalie Cruz ^{[1
]}

Balestrin, Diego ^{[1
]}

Fernandes Filho, Elpidio Inacio ^{[1
]}

da Costa, Liovando Marciano ^{[1
]}

Zeferino, Leiliane Bozzi ^{[1
]}

机构：

[1] Univ Fed Vicosa UFV, Av Peter Henry Rolfs S-N,Campus Univ, BR-36570000 Vicosa, MG, Brazil

来源：

FLORESTA E AMBIENTE | 2020年 / 27卷 / 03期

关键词：

fires; modeling; environmental monitoring;

D O I：

10.1590/2179-8087.011518

中图分类号：

S7 [林业];

学科分类号：

0829 ; 0907 ;

摘要：

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.

引用

页数：7

共 50 条

[1] Outlier Prediction Using Random Forest Classifier
Mohandoss, Divya Pramasani
Shi, Yong
Suo, Kun
[J]. 2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2021, : 27 - 33
[2] Alfalfa cultivars under areas of influence of the Atlantic Forest in the Minas Gerais State, Brazil
Botrel, MD
Ferreira, RD
Alvim, MJ
Xavier, DF
[J]. PESQUISA AGROPECUARIA BRASILEIRA, 2001, 36 (11) : 1437 - 1442
[3] PERFORMANCE OF THE PUBLIC FOREST FOMENTATION OF MINAS GERAIS STATE
Cordeiro, Sidney Araujo
da Silva, Marcio Lopes
Goncalves Jacovine, Laercio Antonio
Valverde, Sebastiao Renato
Rocha, Jose Ludgero
Soares, Naisy Silva
[J]. CERNE, 2009, 15 (03) : 273 - 281
[4] CHARACTERIZATION OF A FOREST INCENTIVE PROGRAM IN MINAS GERAIS STATE
Pereira de Rezende, Jose Luiz
Jorge de Padua, Claudio Tulio
de Oliveira, Antonio Donizette
Soares Scolforo, Jose Roberto
Coelho Junior, Luiz Moreira
[J]. CERNE, 2009, 15 (03) : 295 - 302
[5] DOCUMENTAL ANALYSIS OF FOREST MANAGEMENT PLANS IN FOREST FORMATION AREAS IN MINAS GERAIS
da Silva Coelho, Danilo Jose
da Silva, Agostinho Lopes
Boechat Soares, Carlos Pedro
Romarco de Oliveira, Marcio Leles
de Freitas, Joberto Veloso
[J]. REVISTA ARVORE, 2008, 32 (01): : 69 - 80
[6] Prediction of Incident Delirium Using a Random Forest classifier
John P. Corradi
Stephen Thompson
Jeffrey F. Mather
Christine M. Waszynski
Robert S. Dicks
[J]. Journal of Medical Systems, 2018, 42
[7] Prediction of Incident Delirium Using a Random Forest classifier
Corradi, John P.
Thompson, Stephen
Mather, Jeffrey F.
Waszynski, Christine M.
Dicks, Robert S.
[J]. JOURNAL OF MEDICAL SYSTEMS, 2018, 42 (12)
[8] Richness, composition and similarity of bird community in forest remnants and anthropic areas at southern of Minas Gerais state
de Moura, Aloysio Souza
Correa, Bruno Senna
Machado, Felipe Santana
[J]. REVISTA AGROGEOAMBIENTAL, 2015, 7 (01) : 41 - 52
[9] Football Match Result Prediction Using the Random Forest Classifier
Pugsee, Pakawan
Pattawong, Pattarachai
[J]. PROCEEDINGS OF 2019 2ND INTERNATIONAL CONFERENCE ON BIG DATA TECHNOLOGIES (ICBDT 2019), 2019, : 154 - 158
[10] Default Risk Prediction Using Random Forest and XGBoosting Classifier
Sharma, Alok Kumar
Li, Li-Hua
Ahmad, Ramli
[J]. 2021 INTERNATIONAL CONFERENCE ON SECURITY AND INFORMATION TECHNOLOGIES WITH AI, INTERNET COMPUTING AND BIG-DATA APPLICATIONS, 2023, 314 : 91 - 101

← 1 2 3 4 5 →