Estimating the spatial pattern of human-caused forest fires using a generalized linear mixed model with spatial autocorrelation in South Korea

Hanbin Kwak, Woo-Kyun Lee, Joachim Saborowski, Si Young Lee, Myoung Soo Won, Kyo Sang Koo, Myung Bo Lee, Su Na Kim

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Most forest fires in Korea are spatially concentrated in certain areas and are highly related to human activities. These site-specific characteristics of forest fires are analyzed by spatial regression analysis using the R-module generalized linear mixed model (GLMM), which can consider spatial autocorrelation. We examined the quantitative effect of topology, human accessibility, and forest cover without and with spatial autocorrelation. Under the assumption that slope, elevation, aspect, population density, distance from road, and forest cover are related to forest fire occurrence, the explanatory variables of each of these factors were prepared using a Geographic Information System-based process. First, we tried to test the influence of fixed effects on the occurrence of forest fires using a generalized linear model (GLM) with Poisson distribution. In addition, the overdispersion of the response data was also detected, and variogram analysis was performed using the standardized residuals of GLM. Second, GLMM was applied to consider the obvious residual autocorrelation structure. The fitted models were validated and compared using the multiple correlation and root mean square error (RMSE). Results showed that slope, elevation, aspect index, population density, and distance from road were significant factors capable of explaining the forest fire occurrence. Positive spatial autocorrelation was estimated up to a distance of 32 km. The kriging predictions based on GLMM were smoother than those of the GLM. Finally, a forest fire occurrence map was prepared using the results from both models. The fire risk decreases with increasing distance to areas with high population densities, and increasing elevation showed a suppressing effect on fire occurrence. Both variables are in accordance with the significance tests.

Original languageEnglish
Pages (from-to)1589-1602
Number of pages14
JournalInternational Journal of Geographical Information Science
Volume26
Issue number9
DOIs
Publication statusPublished - 2012 Sep 1

Fingerprint

forest fire
Autocorrelation
South Korea
autocorrelation
Fires
population density
linear model
forest cover
road
significance test
Poisson distribution
variogram
kriging
Regression analysis
Mean square error
accessibility
Geographic information systems
topology
Korea
regression analysis

Keywords

  • forest fire
  • GLMM
  • spatial statistics
  • variogram
  • word

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development
  • Library and Information Sciences

Cite this

Estimating the spatial pattern of human-caused forest fires using a generalized linear mixed model with spatial autocorrelation in South Korea. / Kwak, Hanbin; Lee, Woo-Kyun; Saborowski, Joachim; Lee, Si Young; Won, Myoung Soo; Koo, Kyo Sang; Lee, Myung Bo; Kim, Su Na.

In: International Journal of Geographical Information Science, Vol. 26, No. 9, 01.09.2012, p. 1589-1602.

Research output: Contribution to journalArticle

Kwak, Hanbin ; Lee, Woo-Kyun ; Saborowski, Joachim ; Lee, Si Young ; Won, Myoung Soo ; Koo, Kyo Sang ; Lee, Myung Bo ; Kim, Su Na. / Estimating the spatial pattern of human-caused forest fires using a generalized linear mixed model with spatial autocorrelation in South Korea. In: International Journal of Geographical Information Science. 2012 ; Vol. 26, No. 9. pp. 1589-1602.
@article{b9194764158945f0a4beacc53a219eef,
title = "Estimating the spatial pattern of human-caused forest fires using a generalized linear mixed model with spatial autocorrelation in South Korea",
abstract = "Most forest fires in Korea are spatially concentrated in certain areas and are highly related to human activities. These site-specific characteristics of forest fires are analyzed by spatial regression analysis using the R-module generalized linear mixed model (GLMM), which can consider spatial autocorrelation. We examined the quantitative effect of topology, human accessibility, and forest cover without and with spatial autocorrelation. Under the assumption that slope, elevation, aspect, population density, distance from road, and forest cover are related to forest fire occurrence, the explanatory variables of each of these factors were prepared using a Geographic Information System-based process. First, we tried to test the influence of fixed effects on the occurrence of forest fires using a generalized linear model (GLM) with Poisson distribution. In addition, the overdispersion of the response data was also detected, and variogram analysis was performed using the standardized residuals of GLM. Second, GLMM was applied to consider the obvious residual autocorrelation structure. The fitted models were validated and compared using the multiple correlation and root mean square error (RMSE). Results showed that slope, elevation, aspect index, population density, and distance from road were significant factors capable of explaining the forest fire occurrence. Positive spatial autocorrelation was estimated up to a distance of 32 km. The kriging predictions based on GLMM were smoother than those of the GLM. Finally, a forest fire occurrence map was prepared using the results from both models. The fire risk decreases with increasing distance to areas with high population densities, and increasing elevation showed a suppressing effect on fire occurrence. Both variables are in accordance with the significance tests.",
keywords = "forest fire, GLMM, spatial statistics, variogram, word",
author = "Hanbin Kwak and Woo-Kyun Lee and Joachim Saborowski and Lee, {Si Young} and Won, {Myoung Soo} and Koo, {Kyo Sang} and Lee, {Myung Bo} and Kim, {Su Na}",
year = "2012",
month = "9",
day = "1",
doi = "10.1080/13658816.2011.642799",
language = "English",
volume = "26",
pages = "1589--1602",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor and Francis Ltd.",
number = "9",

}

TY - JOUR

T1 - Estimating the spatial pattern of human-caused forest fires using a generalized linear mixed model with spatial autocorrelation in South Korea

AU - Kwak, Hanbin

AU - Lee, Woo-Kyun

AU - Saborowski, Joachim

AU - Lee, Si Young

AU - Won, Myoung Soo

AU - Koo, Kyo Sang

AU - Lee, Myung Bo

AU - Kim, Su Na

PY - 2012/9/1

Y1 - 2012/9/1

N2 - Most forest fires in Korea are spatially concentrated in certain areas and are highly related to human activities. These site-specific characteristics of forest fires are analyzed by spatial regression analysis using the R-module generalized linear mixed model (GLMM), which can consider spatial autocorrelation. We examined the quantitative effect of topology, human accessibility, and forest cover without and with spatial autocorrelation. Under the assumption that slope, elevation, aspect, population density, distance from road, and forest cover are related to forest fire occurrence, the explanatory variables of each of these factors were prepared using a Geographic Information System-based process. First, we tried to test the influence of fixed effects on the occurrence of forest fires using a generalized linear model (GLM) with Poisson distribution. In addition, the overdispersion of the response data was also detected, and variogram analysis was performed using the standardized residuals of GLM. Second, GLMM was applied to consider the obvious residual autocorrelation structure. The fitted models were validated and compared using the multiple correlation and root mean square error (RMSE). Results showed that slope, elevation, aspect index, population density, and distance from road were significant factors capable of explaining the forest fire occurrence. Positive spatial autocorrelation was estimated up to a distance of 32 km. The kriging predictions based on GLMM were smoother than those of the GLM. Finally, a forest fire occurrence map was prepared using the results from both models. The fire risk decreases with increasing distance to areas with high population densities, and increasing elevation showed a suppressing effect on fire occurrence. Both variables are in accordance with the significance tests.

AB - Most forest fires in Korea are spatially concentrated in certain areas and are highly related to human activities. These site-specific characteristics of forest fires are analyzed by spatial regression analysis using the R-module generalized linear mixed model (GLMM), which can consider spatial autocorrelation. We examined the quantitative effect of topology, human accessibility, and forest cover without and with spatial autocorrelation. Under the assumption that slope, elevation, aspect, population density, distance from road, and forest cover are related to forest fire occurrence, the explanatory variables of each of these factors were prepared using a Geographic Information System-based process. First, we tried to test the influence of fixed effects on the occurrence of forest fires using a generalized linear model (GLM) with Poisson distribution. In addition, the overdispersion of the response data was also detected, and variogram analysis was performed using the standardized residuals of GLM. Second, GLMM was applied to consider the obvious residual autocorrelation structure. The fitted models were validated and compared using the multiple correlation and root mean square error (RMSE). Results showed that slope, elevation, aspect index, population density, and distance from road were significant factors capable of explaining the forest fire occurrence. Positive spatial autocorrelation was estimated up to a distance of 32 km. The kriging predictions based on GLMM were smoother than those of the GLM. Finally, a forest fire occurrence map was prepared using the results from both models. The fire risk decreases with increasing distance to areas with high population densities, and increasing elevation showed a suppressing effect on fire occurrence. Both variables are in accordance with the significance tests.

KW - forest fire

KW - GLMM

KW - spatial statistics

KW - variogram

KW - word

UR - http://www.scopus.com/inward/record.url?scp=84866672848&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866672848&partnerID=8YFLogxK

U2 - 10.1080/13658816.2011.642799

DO - 10.1080/13658816.2011.642799

M3 - Article

AN - SCOPUS:84866672848

VL - 26

SP - 1589

EP - 1602

JO - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

IS - 9

ER -