What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests
Futao Guo A , Guangyu Wang A B , Zhangwen Su A , Huiling Liang C , Wenhui Wang A , Fangfang Lin C and Aiqin Liu A D
+ Author Affiliations
- Author Affiliations
A College of Forestry, Fujian Agriculture and Forestry University, Fuzhou, 350002, China.
B Sustainable Forest Management Laboratory, Faculty of Forestry, University of British Columbia, Vancouver, BC V6T 1Z4, Canada.
C College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, 350002, China.
D Corresponding author. Email: fjlaq@126.com
International Journal of Wildland Fire 25(5) 505-519 https://doi.org/10.1071/WF15121
Submitted: 1 July 2015 Accepted: 28 January 2016 Published: 27 April 2016
Abstract
We applied logistic regression and Random Forest to evaluate drivers of fire occurrence on a provincial scale. Potential driving factors were divided into two groups according to scale of influence: ‘climate factors’, which operate on a regional scale, and ‘local factors’, which includes infrastructure, vegetation, topographic and socioeconomic data. The groups of factors were analysed separately and then significant factors from both groups were analysed together. Both models identified significant driving factors, which were ranked in terms of relative importance. Results show that climate factors are the main drivers of fire occurrence in the forests of Fujian, China. Particularly, sunshine hours, relative humidity (fire seasonal and daily), precipitation (fire season) and temperature (fire seasonal and daily) were seen to play a crucial role in fire ignition. Of the local factors, elevation, distance to railway and per capita GDP were found to be most significant. Random Forest demonstrated a higher predictive ability than logistic regression across all groups of factors (climate, local, and climate and local combined). Maps of the likelihood of fire occurrence in Fujian illustrate that the high fire-risk zones are distributed across administrative divisions; consequently, fire management strategies should be devised based on fire-risk zones, rather than on separate administrative divisions.
Additional keywords: climate factors, driving factors, forest fire prediction, prediction accuracy, wildfire ignition.
References
Abatzoglou JT, Kolden CA (2011) Relative importance of weather and climate on wildfire growth in interior Alaska. International Journal of Wildland Fire 20, 479–486.| Relative importance of weather and climate on wildfire growth in interior Alaska.Crossref | GoogleScholarGoogle Scholar |
Abdel-Rahman EM, Ahmed FB, Ismail R (2013) Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data. International Journal of Remote Sensing 34, 712–728.
| Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data.Crossref | GoogleScholarGoogle Scholar |
Ali AA, Carcaillet C, Bergeron Y (2009) Long-term fire frequency variability in the eastern Canadian boreal forest: the influences of climate vs. local factors. Global Change Biology 15, 1230–1241.
| Long-term fire frequency variability in the eastern Canadian boreal forest: the influences of climate vs. local factors.Crossref | GoogleScholarGoogle Scholar |
Amraoui M, Pereira MG, DaCamara CC, Calado TJ (2015) Atmospheric conditions associated with extreme fire activity in the Western Mediterranean region. The Science of the Total Environment 524–525, 32–39.
| Atmospheric conditions associated with extreme fire activity in the Western Mediterranean region.Crossref | GoogleScholarGoogle Scholar | 25889542PubMed |
Archibald S, Roy DP, van Wilgen BW, Scholes RJ (2009) What limits fire? An examination of drivers of burnt area in Southern Africa. Global Change Biology 15, 613–630.
| What limits fire? An examination of drivers of burnt area in Southern Africa.Crossref | GoogleScholarGoogle Scholar |
Bergeron Y, Gauthier S, Flannigan M, Kafka V (2004) Fire regimes at the transition between mixedwood and coniferous boreal forest in northwestern Quebec. Ecology 85, 1916–1932.
| Fire regimes at the transition between mixedwood and coniferous boreal forest in northwestern Quebec.Crossref | GoogleScholarGoogle Scholar |
Breiman L (2001) Random forests. Machine Learning 45, 5–32.
| Random forests.Crossref | GoogleScholarGoogle Scholar |
Cardille JA, Ventura SJ, Turner MG (2001) Environmental and social factors influencing wildfires in the upper midwest United States. Ecological Applications 11, 111–127.
| Environmental and social factors influencing wildfires in the upper midwest United States.Crossref | GoogleScholarGoogle Scholar |
Castro FX, Tudela A, Sebastiá MA (2003) Modeling moisture content in shrubs to predict fire risk in Catalonia (Spain). Agricultural and Forest Meteorology 116, 49–59.
| Modeling moisture content in shrubs to predict fire risk in Catalonia (Spain).Crossref | GoogleScholarGoogle Scholar |
Catry FX, Rego FC, Bacão FL, Moreira F (2009) Modeling and mapping wildfire ignition risk in Portugal. International Journal of Wildland Fire 18, 921–931.
| Modeling and mapping wildfire ignition risk in Portugal.Crossref | GoogleScholarGoogle Scholar |
Chang Y, Zhu ZL, Bu RC, Chen HG, Feng YT, Li YH, Hu YM, Wang ZC (2013) Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China. Landscape Ecology 28, 1989–2004.
| Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China.Crossref | GoogleScholarGoogle Scholar |
Chas-Amil ML, Prestemon JP, McClean CJ, Touza J (2015) Human-ignited wildfire patterns and responses to policy shifts. Applied Geography (Sevenoaks, England) 56, 164–176.
| Human-ignited wildfire patterns and responses to policy shifts.Crossref | GoogleScholarGoogle Scholar |
Chéret V, Denux JP (2011) Analysis of MODIS NDVI time series to calculate indicators of Mediterranean forest fire susceptibility. GIScience & Remote Sensing 48, 171–194.
| Analysis of MODIS NDVI time series to calculate indicators of Mediterranean forest fire susceptibility.Crossref | GoogleScholarGoogle Scholar |
Chuvieco E, Cocero D, Riaño D, Martin P, Martínez-Vega J, de la Riva J, Pérez F (2004) Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating. Remote Sensing of Environment 92, 322–331.
| Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating.Crossref | GoogleScholarGoogle Scholar |
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88, 2783–2792.
| Random forests for classification in ecology.Crossref | GoogleScholarGoogle Scholar | 18051647PubMed |
De Angelis A, Bajocco S, Ricotta C (2012) Modelling the phenological niche of large fires with remotely sensed NDVI profiles. Ecological Modelling 228, 106–111.
| Modelling the phenological niche of large fires with remotely sensed NDVI profiles.Crossref | GoogleScholarGoogle Scholar |
Duro DC, Franklin SE, Dube MG (2012) Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests. International Journal of Remote Sensing 33, 4502–4526.
| Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests.Crossref | GoogleScholarGoogle Scholar |
Ganteaume A, Jappiot M (2013) What causes large fires in Southern France. Forest Ecology and Management 294, 76–85.
| What causes large fires in Southern France.Crossref | GoogleScholarGoogle Scholar |
Garcia CV, Woodard P, Titus S, Adamowicz W, Lee B (1995) A logit model for predicting the daily occurrence of human caused forest-fires. International Journal of Wildland Fire 5, 101–111.
| A logit model for predicting the daily occurrence of human caused forest-fires.Crossref | GoogleScholarGoogle Scholar |
García CV, Tatay-Nieto J, Blanco R, Chuvieco E (2010) Evaluation of the influence of local fuel homogeneity on fire hazard through Landsat-5 TM texture measures. Photogrammetric Engineering and Remote Sensing 76, 853–864.
| Evaluation of the influence of local fuel homogeneity on fire hazard through Landsat-5 TM texture measures.Crossref | GoogleScholarGoogle Scholar |
Genuer R, Poggi JM, Tuleau-Malot C (2010) Variable selection using random forests. Pattern Recognition Letters 31, 2225–2236.
| Variable selection using random forests.Crossref | GoogleScholarGoogle Scholar |
Grõmping U (2009) Variable importance assessment in regression: linear regression versus random forest. The American Statistician 63, 308–319.
| Variable importance assessment in regression: linear regression versus random forest.Crossref | GoogleScholarGoogle Scholar |
Guo FT, Innes JL, Wang GY, Ma XQ, Sun L, Hu HQ, Su ZW (2015) Historic distribution and driving factors of human-caused fires in the Chinese boreal forest between 1972 and 2005. Journal of Plant Ecology 8, 480–490.
| Historic distribution and driving factors of human-caused fires in the Chinese boreal forest between 1972 and 2005.Crossref | GoogleScholarGoogle Scholar |
Gutman G, Ignatov A (1998) The derivation of the green vegetation fraction from NOAA/AVHRR data for use in numerical weather prediction models. International Journal of Remote Sensing 19, 1533–1543.
| The derivation of the green vegetation fraction from NOAA/AVHRR data for use in numerical weather prediction models.Crossref | GoogleScholarGoogle Scholar |
He ZH, Liu XD, Zhao H, Zhou JQ (2013) Forest flammability and temporal and spatial distribution rules of forest fire in Jiangle County of Fujian Province. Hunan Agricultural Sciences 7, 108–111. . Available at http://en.cnki.com.cn/Article_en/CJFDTotal-HNNK201307034.htm [Verified 23 March 2016]
Hering A, Bell C, Genton M (2009) Modeling spatio-temporal wildfire ignition point patterns. Environmental and Ecological Statistics 16, 225–250.
| Modeling spatio-temporal wildfire ignition point patterns.Crossref | GoogleScholarGoogle Scholar |
Jiménez-Valverde A (2012) Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modeling. Global Ecology and Biogeography 21, 498–507.
| Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modeling.Crossref | GoogleScholarGoogle Scholar |
Jing WL, Feng M, Yang YP (2013) A statistical downscaling approach of NCEP/NCAR reanalysis temperature data. Journal of Geo-information Science 15, 819–828.
| A statistical downscaling approach of NCEP/NCAR reanalysis temperature data.Crossref | GoogleScholarGoogle Scholar |
Johnson EA, Larsen CPS (1991) Climatically induced change in fire frequency in the Southern Canadian Rockies. Ecology 72, 194–201.
| Climatically induced change in fire frequency in the Southern Canadian Rockies.Crossref | GoogleScholarGoogle Scholar |
Justice CO, Giglio L, Korontzi S, Owens J, Morisette JT, Roy D, Descloitres J, Alleaume S, Petitcolin F, Kaufman Y (2002) The MODIS fire products. Remote Sensing of Environment 83, 244–262.
| The MODIS fire products.Crossref | GoogleScholarGoogle Scholar |
Li XW, Zhao G, Yu XB, Yu Q (2014) A comparison of forest fire indices for predicting fire risk in contrasting climates in China. Natural Hazards 70, 1339–1356.
| A comparison of forest fire indices for predicting fire risk in contrasting climates in China.Crossref | GoogleScholarGoogle Scholar |
Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2, 18–22. [Verified 10 February 2016]http://cogns.northwestern.edu/cbmg/LiawAndWiener2002.pdf
Littell JS, Mckenzie D, Peterson DL, Westerling AL (2009) Climate and wildfire area burned in western U.S. ecoprovinces, 1916–2003. Ecological Applications 19, 1003–1021.
| Climate and wildfire area burned in western U.S. ecoprovinces, 1916–2003.Crossref | GoogleScholarGoogle Scholar | 19544740PubMed |
Liu Z, Yang J, Chang Y, Weisberg PJ, He HS (2012) Spatial patterns and drivers of fire occurrence and its future trend under climate change in a boreal forest of Northeast China. Global Change Biology 18, 2041–2056.
| Spatial patterns and drivers of fire occurrence and its future trend under climate change in a boreal forest of Northeast China.Crossref | GoogleScholarGoogle Scholar |
Lv JW, Yue Q, Wang Z, Zhang GJ (2010) Carbon sequestration potential in Fujian’s forest ecosystems. Acta Ecologica Sinica 30, 2188–2196.
Maingi JK, Henry MC (2007) Factors influencing wildfire occurrence and distribution in eastern Kentucky, USA. International Journal of Wildland Fire 16, 23–33.
| Factors influencing wildfire occurrence and distribution in eastern Kentucky, USA.Crossref | GoogleScholarGoogle Scholar |
Marston CG, Mark Danson F, Armitage RP, Patrick Giraudoux P, Pleydell DRJ, Wang Q, Qui JM, Craig PS (2014) A random forest approach for predicting the presence of Echinococcus multilocularis intermediate host Ochotona spp. presence in relation to landscape characteristics in western China. Applied Geography (Sevenoaks, England) 55, 176–183.
| A random forest approach for predicting the presence of Echinococcus multilocularis intermediate host Ochotona spp. presence in relation to landscape characteristics in western China.Crossref | GoogleScholarGoogle Scholar |
Martínez J, García CV, Chuvieco E (2009) Human-caused wildfire risk rating for prevention planning in Spain. Journal of Environmental Management 90, 1241–1252.
| Human-caused wildfire risk rating for prevention planning in Spain.Crossref | GoogleScholarGoogle Scholar | 18723267PubMed |
Minnich RA, Bahre CJ (1995) Wildland fire and chaparral succession along the California–Baja California boundary. International Journal of Wildland Fire 5, 13–24.
| Wildland fire and chaparral succession along the California–Baja California boundary.Crossref | GoogleScholarGoogle Scholar |
Miranda BR, Sturtevant BR, Stewart SI, Hammer RB (2012) Spatial and temporal drivers of wildfire occurrence in the context of rural development in northern Wisconsin, USA. International Journal of Wildland Fire 21, 141–154.
| Spatial and temporal drivers of wildfire occurrence in the context of rural development in northern Wisconsin, USA.Crossref | GoogleScholarGoogle Scholar |
Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira JMC (2012) Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest. Forest Ecology and Management 275, 117–129.
| Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest.Crossref | GoogleScholarGoogle Scholar |
Pereira MG, Trigo RM, da Camara CC, Pereira JM, Leite SM (2005) Synoptic patterns associated with large summer forest fires in Portugal. Agricultural and Forest Meteorology 129, 11–25.
| Synoptic patterns associated with large summer forest fires in Portugal.Crossref | GoogleScholarGoogle Scholar |
Pereira MG, Malamud BD, Trigo RM, Alves PI (2011) The history and characteristics of the 1980–2005 Portuguese rural fire database. Natural Hazards and Earth System Sciences 11, 3343–3358.
| The history and characteristics of the 1980–2005 Portuguese rural fire database.Crossref | GoogleScholarGoogle Scholar |
Pereira MG, Caramelo L, Orozco CV, Costa R, Tonini M (2015) Space-time clustering analysis performance of an aggregated dataset: the case of wildfires in Portugal. Environmental Modelling & Software 72, 239–249.
| Space-time clustering analysis performance of an aggregated dataset: the case of wildfires in Portugal.Crossref | GoogleScholarGoogle Scholar |
Pew KL, Larsen CPS (2001) GIS analysis of spatial and temporal patterns of human-caused wildfires in the temperate rain forest of Vancouver Island, Canada. Forest Ecology and Management 140, 1–18.
| GIS analysis of spatial and temporal patterns of human-caused wildfires in the temperate rain forest of Vancouver Island, Canada.Crossref | GoogleScholarGoogle Scholar |
Podur J, Martell DL, Csillag F (2003) Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998. Ecological Modelling 164, 1–20.
| Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998.Crossref | GoogleScholarGoogle Scholar |
Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9, 181–199.
| Newer classification and regression tree techniques: bagging and random forests for ecological prediction.Crossref | GoogleScholarGoogle Scholar |
Prasad VK, Badarinathb KVS, Eaturu A (2008) Biophysical and anthropogenic controls of forest fires in the Deccan Plateau, India. Journal of Environmental Management 86, 1–13.
| Biophysical and anthropogenic controls of forest fires in the Deccan Plateau, India.Crossref | GoogleScholarGoogle Scholar | 17275159PubMed |
Purevdorj T, Tateishi R, Ishiyama T, Honda Y (1998) Relationships between percent vegetation cover and vegetation indices. International Journal of Remote Sensing 19, 3519–3535.
| Relationships between percent vegetation cover and vegetation indices.Crossref | GoogleScholarGoogle Scholar |
Ren Y, Wei XH, Zhang L, Cui SH, Chen F, Xiong YZ, Xie (2011) Potential for forest vegetation carbon storage in Fujian Province, China, determined from forest inventories. Plant and Soil 345, 125–140.
| Potential for forest vegetation carbon storage in Fujian Province, China, determined from forest inventories.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC3MXptFymtL4%3D&md5=7ae0a835ab6347c1615b07fde5f65ae9CAS |
Rodrigues M, de al Riva J, Fotheringham S (2014) Modeling the spatial variation of the explanatory factors of human-caused wildfires in Spain using geographically weighted logistic regression. Applied Geography (Sevenoaks, England) 48, 52–63.
| Modeling the spatial variation of the explanatory factors of human-caused wildfires in Spain using geographically weighted logistic regression.Crossref | GoogleScholarGoogle Scholar |
Romero-Calcerrada R, Barrio-Parra F, Millington JDA, Novillo CJ (2010) Spatial modeling of socioeconomic data to understand patterns of human-caused wildfire ignition risk in the SW of Madrid (central Spain). Ecological Modelling 221, 34–45.
| Spatial modeling of socioeconomic data to understand patterns of human-caused wildfire ignition risk in the SW of Madrid (central Spain).Crossref | GoogleScholarGoogle Scholar |
Rothermel RC (1991) Predicting behavior and size of crown fires in the northern Rocky Mountains. USDA Forest Service, Intermountain Forest and Range Experiment Station, Research Paper RP-INT-438. (Ogden, UT) Available at http://digitalcommons.usu.edu/barkbeetles/69/ [Verified 23 March 2016]
Schulte LA, Mladenoff DJ (2005) Severe wind and fire regimes in northern forests: historical variability at the regional scale. Ecology 86, 431–445.
| Severe wind and fire regimes in northern forests: historical variability at the regional scale.Crossref | GoogleScholarGoogle Scholar |
State Forestry Administration of P. R. China (2014) ‘China Forestry Statistical Yearbook 2013.’ (China Forestry Publishing House: Beijing)
Sturtevant BR, Cleland DT (2007) Human and biophysical factors influencing modern fire disturbance in northern Wisconsin. International Journal of Wildland Fire 16, 398–413.
| Human and biophysical factors influencing modern fire disturbance in northern Wisconsin.Crossref | GoogleScholarGoogle Scholar |
Syphard AD, Radeloff VC, Keeley JE, Hawbaker TJ, Clayton MK, Stewart SI, Hammer RB (2007) Human influence on California fire regimes. Ecological Applications 17, 1388–1402.
| Human influence on California fire regimes.Crossref | GoogleScholarGoogle Scholar | 17708216PubMed |
Syphard AD, Radeloff VC, Keuler NS, Taylor RS, Hawbaker TJ, Stewart SI, Clayton MK (2008) Predicting spatial patterns of fire on a southern California landscape. International Journal of Wildland Fire 17, 602–613.
| Predicting spatial patterns of fire on a southern California landscape.Crossref | GoogleScholarGoogle Scholar |
Turco M, Llasat MC, Hardenberg J, Provenzale A (2013) Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula). Climatic Change 116, 665–678.
| Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula).Crossref | GoogleScholarGoogle Scholar |
Vilar L, Woolford DG, Martell DL, Pilar Martín M (2010) A model for predicting human-caused wildfire occurrence in the region of Madrid, Spain. International Journal of Wildland Fire 19, 325–337.
| A model for predicting human-caused wildfire occurrence in the region of Madrid, Spain.Crossref | GoogleScholarGoogle Scholar |
Vilar del Hoyo L, Martín Isabel M, Martínez Vega F (2011) Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data. European Journal of Forest Research 130, 983–996.
| Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data.Crossref | GoogleScholarGoogle Scholar |
Wotton BM, Martell DL, Logan KA (2003) Climate change and people-caused forest fire occurrence in Ontario. Climatic Change 60, 275–295.
| Climate change and people-caused forest fire occurrence in Ontario.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3sXnvVOrs78%3D&md5=92f7cde8574f244b644c71604f1c55cfCAS |
Wu ZW, He HS, Yang J, Liu ZH, Liang Y (2014) Relative effects of climatic and local factors on fire occurrence in boreal forest landscapes of northeastern China. The Science of the Total Environment 493, 472–480.
| Relative effects of climatic and local factors on fire occurrence in boreal forest landscapes of northeastern China.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC2cXhtFyktLjI&md5=c96d02d60c9aef24ad020b4d09f5ebfdCAS |
Wu ZW, He HS, Yang J, Liang Y (2015) Defining fire environment zones in the boreal forests of northeastern China. The Science of the Total Environment 518–519, 106–116.
| Defining fire environment zones in the boreal forests of northeastern China.Crossref | GoogleScholarGoogle Scholar |
Yang YP (2014) Annual average climate data set of China with 1km grid resolution. Data Sharing Infrastructure of Earth System Science. Available at http://www.geodata.cn/Portal/index.jsp [Verified 12 December 2015]
Zhang B (1995) An approach to the occurrence characteristics and control countermeasures of forest fires in Fujian. Journal of Fujian Forestry Science and Technology 22, 81–84. . Available at http://en.cnki.com.cn/Article_en/CJFDTOTAL-FJLK504.017.htm [Verified 10 February 2016]
Zhang ZX, Zhang HY, Zhou DW (2010) Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires. Journal of Arid Environments 74, 386–393.
| Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires.Crossref | GoogleScholarGoogle Scholar |
Zheng HQ, Chen JP, Zhang X, Zhang CA, Zhang CG, Chen H (2001) Study on the forecast system of forest fire weather ranks in Fujian. Chinese Journal of Agrometeorology 3, 38–50. . Available at http://en.cnki.com.cn/Article_en/CJFDTOTAL-ZGNY200103008.htm [Verified 29 March 2016]
Zumbrunnen T, Pezzatti GB, Menéndezd P, Bugmann H, Bürgi M, Conedera M (2011) Weather and human impacts on forest fires: 100 years of fire history in two climatic regions of Switzerland. Forest Ecology and Management 261, 2188–2199.
| Weather and human impacts on forest fires: 100 years of fire history in two climatic regions of Switzerland.Crossref | GoogleScholarGoogle Scholar |
