Factors Influencing Regional-Scale Wildfire Probability in Iran

Abstract This study was conducted to gain a better understanding of factors influencing regional-scale wildfire probability and its spatial distribution. The random forest model was employed to investigate the spatial association between historical fire events in the Zagros Mountains (Iran) and different geo-environmental factors to characterize regional-scale trends of wildfire occurrences. Among the factors considered, proximity to human settlements (Gini = 9.38), annual rainfall (Gini = 8.85), altitude (Gini = 7.41), and proximity to roads (Gini = 7.40) were identified as the most effective factors. To predict future ignitions and to delineate the study area to different levels of wildfire probability, the support vector machine model was applied and proved to be an effective model with satisfactory accuracy (success rate = 0.81; prediction rate = 0.75). The insights obtained from this research can be applied to spatially explicit assessment of fire-prone landscapes and decision-making for wildfire management.

[1]  Biswajeet Pradhan,et al.  A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India) , 2016, Environ. Model. Softw..

[2]  H. Pourghasemi,et al.  Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran , 2016, Environmental Earth Sciences.

[3]  Jian Yang,et al.  Spatial Patterns of Modern Period Human-Caused Fire Occurrence in the Missouri Ozark Highlands , 2007, Forest Science.

[4]  F. Mouillot,et al.  Contribution of human and biophysical factors to the spatial distribution of forest fire ignitions and large wildfires in a French Mediterranean region , 2017 .

[5]  J. Greenberg,et al.  Spatial variability in wildfire probability across the western United States , 2012 .

[6]  K. Solaimani,et al.  Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques , 2012, Natural Hazards.

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

[8]  L. Mearns,et al.  Climate Change and Forest Fire Potential in Russian and Canadian Boreal Forests , 1998 .

[9]  H. Pourghasemi,et al.  Prediction of the landslide susceptibility: Which algorithm, which precision? , 2018 .

[10]  A. Zhu,et al.  Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China. , 2018, The Science of the total environment.

[11]  Hamid Reza Pourghasemi,et al.  A comparative assessment of prediction capabilities of modified analytical hierarchy process (M-AHP) and Mamdani fuzzy logic models using Netcad-GIS for forest fire susceptibility mapping , 2016 .

[12]  A. Weaver,et al.  Detecting the effect of climate change on Canadian forest fires , 2004 .

[13]  Dieu Tien Bui,et al.  Tropical Forest Fire Susceptibility Mapping at the Cat Ba National Park Area, Hai Phong City, Vietnam, Using GIS-Based Kernel Logistic Regression , 2016, Remote. Sens..

[14]  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.

[15]  Zohre Sadat Pourtaghi,et al.  Investigation of general indicators influencing on forest fire and its susceptibility modeling using different data mining techniques , 2016 .

[16]  J. Agee,et al.  Reform forest fire management , 2015, Science.

[17]  Binh Thai Pham,et al.  Wildfire spatial pattern analysis in the Zagros Mountains, Iran: A comparative study of decision tree based classifiers , 2018, Ecol. Informatics.

[18]  Toddi A. Steelman,et al.  Wildfire risk as a socioecological pathology , 2016 .

[19]  Mario Mhawej,et al.  Towards an establishment of a wildfire risk system in a Mediterranean country , 2016, Ecol. Informatics.

[20]  Wildfire hazard mapping using an ensemble method of frequency ratio with Shannon's entropy. , 2017 .

[21]  T. Swetnam,et al.  Managing Forests and Fire in Changing Climates , 2013, Science.

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

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

[24]  K. Solaimani,et al.  Modelling static fire hazard in a semi-arid region using frequency analysis , 2015 .

[25]  Corinne Lampin,et al.  A Review of the Main Driving Factors of Forest Fire Ignition Over Europe , 2013, Environmental Management.

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

[27]  Mahyat Shafapour Tehrany,et al.  Flood susceptibility assessment using GIS-based support vector machine model with different kernel types , 2015 .

[28]  Dieu Tien Bui,et al.  A novel hybrid intelligent model of support vector machines and the MultiBoost ensemble for landslide susceptibility modeling , 2019, Bulletin of Engineering Geology and the Environment.

[29]  Javad Rezaeian,et al.  Prediction of Slope Failures in Support of Forestry Operations Safety , 2017 .

[30]  A. Jaafari,et al.  Spatial prediction of wildfire probability in the Hyrcanian ecoregion using evidential belief function model and GIS , 2018, International Journal of Environmental Science and Technology.

[31]  F. Achard,et al.  The effect of climate anomalies and human ignition factor on wildfires in Russian boreal forests , 2008, Philosophical Transactions of the Royal Society B: Biological Sciences.

[32]  Mike D. Flannigan,et al.  Anthropogenic influence on wildfire activity in Alberta, Canada , 2016 .

[33]  Biswajeet Pradhan,et al.  A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area , 2017 .

[34]  Juan de la Riva,et al.  An insight into machine-learning algorithms to model human-caused wildfire occurrence , 2014, Environ. Model. Softw..

[35]  H. Pourghasemi.  GIS-based forest fire susceptibility mapping in Iran: a comparison between evidential belief function and binary logistic regression models , 2016 .

[36]  Abolfazl Jaafari,et al.  A Bayesian modeling of wildfire probability in the Zagros Mountains, Iran , 2017, Ecol. Informatics.

[37]  Mikhail F. Kanevski,et al.  Wildfire susceptibility mapping: Deterministic vs. stochastic approaches , 2018, Environ. Model. Softw..

[38]  H. Pourghasemi,et al.  Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling. , 2017, The Science of the total environment.

[39]  Manfred F. Buchroithner,et al.  Spatial-statistical analysis of factors determining forest fires: a case study from Golestan, Northeast Iran , 2018 .

[40]  H. Pourghasemi,et al.  GIS-based frequency ratio and index of entropy models for landslide susceptibility assessment in the Caspian forest, northern Iran , 2014, International Journal of Environmental Science and Technology.

[41]  M. Turetsky,et al.  Impacts of climate change on fire activity and fire management in the circumboreal forest , 2009 .

[42]  T. Kavzoglu,et al.  Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression , 2014, Landslides.