What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests

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.

[1]  E. Johnson,et al.  CLIMATICALLY INDUCED CHANGE IN FIRE FREQUENCY IN THE SOUTHERN CANADIAN ROCKIES , 1991 .

[2]  R. Minnich,et al.  Wildland Fire and Chaparral Succession Along the California-Baja California Boundary , 1995 .

[3]  Wiktor L. Adamowicz,et al.  A Logit Model for Predicting the Daily Occurrence of Human Caused Forest-Fires , 1995 .

[4]  R. Tateishi,et al.  Relationships between percent vegetation cover and vegetation indices , 1998 .

[5]  G. Gutman,et al.  The derivation of the green vegetation fraction from NOAA/AVHRR data for use in numerical weather prediction models , 1998 .

[6]  S. Ventura,et al.  ENVIRONMENTAL AND SOCIAL FACTORS INFLUENCING WILDFIRES IN THE UPPER MIDWEST, UNITED STATES , 2001 .

[7]  Zhang Cang-an.  Study on the Forecast System of Forest Fire Weather Ranks in Fujian , 2001 .

[8]  C. Larsen,et al.  GIS analysis of spatial and temporal patterns of human-caused wildfires in the temperate rain forest of Vancouver Island, Canada , 2001 .

[9]  D. Roy,et al.  The MODIS fire products , 2002 .

[10]  B. M. Wotton,et al.  Climate Change and People-Caused Forest Fire Occurrence in Ontario , 2003 .

[11]  A. Tudela,et al.  Modeling moisture content in shrubs to predict fire risk in Catalonia (Spain) , 2003 .

[12]  F. Csillag,et al.  Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998 , 2003 .

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Yves Bergeron,et al.  FIRE REGIMES AT THE TRANSITION BETWEEN MIXEDWOOD AND CONIFEROUS BOREAL FOREST IN NORTHWESTERN QUEBEC , 2004 .

[15]  D. Riaño,et al.  Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating , 2004 .

[16]  David J. Mladenoff,et al.  SEVERE WIND AND FIRE REGIMES IN NORTHERN FORESTS: HISTORICAL VARIABILITY AT THE REGIONAL SCALE , 2005 .

[17]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[18]  José M. C. Pereira,et al.  Synoptic patterns associated with large summer forest fires in Portugal , 2005 .

[19]  John K. Maingi,et al.  Factors Influencing Wildfire Occurrence and Distribution in Eastern Kentucky, USA , 2007 .

[20]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[21]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[22]  Brian R. Sturtevant,et al.  Human and biophysical factors influencing modern fire disturbance in northern Wisconsin , 2007 .

[23]  Susan I. Stewart,et al.  Human influence on California fire regimes. , 2007, Ecological applications : a publication of the Ecological Society of America.

[24]  Marc G. Genton,et al.  Modeling spatio-temporal wildfire ignition point patterns , 2009, Environmental and Ecological Statistics.

[25]  Alexandra D. Syphard,et al.  Predicting spatial patterns of fire on a southern California landscape , 2008 .

[26]  Anuradha Eaturu,et al.  Biophysical and anthropogenic controls of forest fires in the Deccan Plateau, India. , 2008, Journal of environmental management.

[27]  D. Roy,et al.  What limits fire? An examination of drivers of burnt area in Southern Africa , 2009 .

[28]  D. Peterson,et al.  Climate and wildfire area burned in western U.S. ecoprovinces, 1916-2003. , 2009, Ecological applications : a publication of the Ecological Society of America.

[29]  Y. Bergeron,et al.  Long‐term fire frequency variability in the eastern Canadian boreal forest: the influences of climate vs. local factors , 2009 .

[30]  F. Moreira,et al.  Modeling and mapping wildfire ignition risk in Portugal , 2009 .

[31]  U. Grömping.  Dependence of Variable Importance in Random Forests on the Shape of the Regressor Space , 2009 .

[32]  E. Chuvieco,et al.  Human-caused wildfire risk rating for prevention planning in Spain. , 2009, Journal of environmental management.

[33]  Zheng-xiang Zhang,et al.  Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires. , 2010 .

[34]  Carbon sequestration potential in Fujian's forest ecosystems , 2010 .

[35]  Douglas G. Woolford,et al.  A model for predicting human-caused wildfire occurrence in the region of Madrid, Spain , 2010 .

[36]  Carlos J. Novillo,et al.  Spatial modelling of socioeconomic data to understand patterns of human-caused wildfire ignition risk in the SW of Madrid (central Spain) , 2010 .

[37]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[38]  E. Chuvieco,et al.  Evaluation of the Influence of Local Fuel Homogeneity on Fire Hazard through Landsat-5 TM Texture Measures , 2010 .

[39]  Lara Vilar del Hoyo,et al.  Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data , 2011, European Journal of Forest Research.

[40]  V. Chéret,et al.  Analysis of MODIS NDVI Time Series to Calculate Indicators of Mediterranean Forest Fire Susceptibility , 2011 .

[41]  J. Abatzoglou,et al.  Relative importance of weather and climate on wildfire growth in interior Alaska , 2011 .

[42]  Mário G. Pereira,et al.  The history and characteristics of the 1980-2005 Portuguese rural fire database , 2011 .

[43]  Shenghui Cui,et al.  Potential for forest vegetation carbon storage in Fujian Province, China, determined from forest inventories , 2011, Plant and Soil.

[44]  Harald Bugmann,et al.  Weather and human impacts on forest fires: 100 years of fire history in two climatic regions of Switzerland , 2011 .

[45]  Susan I. Stewart,et al.  Spatial and temporal drivers of wildfire occurrence in the context of rural development in northern Wisconsin, USA , 2012 .

[46]  Steven E. Franklin,et al.  Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests , 2012 .

[47]  J. Pereira,et al.  Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest , 2012 .

[48]  A. Jiménez‐Valverde.  Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling , 2012 .

[49]  Yu Chang,et al.  Spatial patterns and drivers of fire occurrence and its future trend under climate change in a boreal forest of Northeast China , 2012 .

[50]  C. Ricotta,et al.  Modelling the phenological niche of large fires with remotely sensed NDVI profiles , 2012 .

[51]  M. Turco,et al.  Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula) , 2013, Climatic Change.

[52]  Yu Chang,et al.  Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China , 2013, Landscape Ecology.

[53]  Forest Flammability and Temporal and Spatial Distribution Rules of Forest Fire in Jiangle County of Fujian Province , 2013 .

[54]  Xiubo Yu,et al.  A comparison of forest fire indices for predicting fire risk in contrasting climates in China , 2013, Natural Hazards.

[55]  Marielle Jappiot,et al.  What causes large fires in Southern France , 2013 .

[56]  Elfatih M. Abdel-Rahman,et al.  Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data , 2013 .

[57]  A Statistical Downscaling Approach of NCEP/NCAR Reanalysis Temperature Data , 2013 .

[58]  S. Fotheringham,et al.  Modeling the spatial variation of the explanatory factors of human-caused wildfires in Spain using geographically weighted logistic regression , 2014 .

[59]  F. M. Danson,et al.  A random forest approach for predicting the presence of Echinococcus multilocularis intermediate host Ochotona spp. presence in relation to landscape characteristics in western China. , 2014, Applied geography.

[60]  Zhihua Liu,et al.  Relative effects of climatic and local factors on fire occurrence in boreal forest landscapes of northeastern China. , 2014, The Science of the total environment.

[61]  Hong S. He,et al.  Defining fire environment zones in the boreal forests of northeastern China. , 2015, The Science of the total environment.

[62]  Teresa J. Calado,et al.  Atmospheric conditions associated with extreme fire activity in the Western Mediterranean region. , 2015, The Science of the total environment.

[63]  John L. Innes,et al.  Historic distribution and driving factors of human-caused fires in the Chinese boreal forest between 1972 and 2005 , 2015 .

[64]  Jeffrey P. Prestemon,et al.  Human-ignited wildfire patterns and responses to policy shifts , 2015 .

[65]  Ricardo Costa,et al.  Space-time clustering analysis performance of an aggregated dataset: The case of wildfires in Portugal , 2015, Environ. Model. Softw..