Application of an Ensemble Statistical Approach in Spatial Predictions of Bushfire Probability and Risk Mapping

The survival of humanity is dependent on the survival of forests and the ecosystems they support, yet annually wildfires destroy millions of hectares of global forestry. Wildfires take place under specific conditions and in certain regions, which can be studied through appropriate techniques. A variety of statistical modeling methods have been assessed by researchers; however, ensemble modeling of wildfire susceptibility has not been undertaken. We hypothesize that ensemble modeling of wildfire susceptibility is better than a single modeling technique. This study models the occurrence of wildfire in the Brisbane Catchment of Australia, which is an annual event, using the index of entropy (IoE), evidential belief function (EBF), and logistic regression (LR) ensemble techniques. As a secondary goal of this research, the spatial distribution of the wildfire risk from different aspects such as urbanization and ecosystem was evaluated. The highest accuracy (88.51%) was achieved using the ensemble EBF and LR model. The outcomes of this study may be helpful to particular groups such as planners to avoid susceptible and risky regions in their planning; model builders to replace the traditional individual methods with ensemble algorithms; and geospatial users to enhance their knowledge of geographic information system (GIS) applications.

[1]  Peter Troch,et al.  Influence of terrain aspect on water partitioning, vegetation structure and vegetation greening in high‐elevation catchments in northern New Mexico , 2016 .

[2]  Jung Hyun Lee,et al.  A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping , 2014 .

[3]  Hamid Reza Pourghasemi,et al.  A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China , 2017, Arabian Journal of Geosciences.

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

[5]  D. Dominey-Howes,et al.  Validating a Tsunami Vulnerability Assessment Model (the PTVA Model) Using Field Data from the 2004 Indian Ocean Tsunami , 2007 .

[6]  Arthur P. Dempster,et al.  Upper and Lower Probabilities Induced by a Multivalued Mapping , 1967, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[7]  S. Page,et al.  In the line of fire: the peatlands of Southeast Asia , 2016, Philosophical Transactions of the Royal Society B: Biological Sciences.

[8]  Wei Chen,et al.  Spatial prediction of landslide susceptibility by combining evidential belief function, logistic regression and logistic model tree , 2019, Geocarto International.

[9]  Geoffrey H. Donovan,et al.  Valuing morbidity effects of wildfire smoke exposure from the 2007 Southern California wildfires , 2016 .

[10]  J. Koprowski,et al.  Differential response to fire by an introduced and an endemic species complicates endangered species conservation , 2016 .

[11]  C. Bryant.  Understanding bushfire : trends in deliberate vegetation fires in Australia , 2008 .

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

[13]  Liba Pejchar,et al.  Mitigation for energy development fails to mimic natural disturbance for birds and mammals , 2017 .

[14]  Nilton Cesar Fiedler,et al.  Applying GIS to develop a model for forest fire risk: A case study in Espírito Santo, Brazil. , 2016, Journal of environmental management.

[15]  Biswajeet Pradhan,et al.  Manifestation of LiDAR-Derived Parameters in the Spatial Prediction of Landslides Using Novel Ensemble Evidential Belief Functions and Support Vector Machine Models in GIS , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Y. Tesfaigzi,et al.  Wildfire smoke exposure and human health: Significant gaps in research for a growing public health issue. , 2017, Environmental toxicology and pharmacology.

[17]  Biswajeet Pradhan,et al.  Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree , 2016, Landslides.

[18]  D. Bromwich,et al.  Recent precipitation trends, flash floods and landslides in southern Brazil , 2016 .

[19]  S. Cumming.  FOREST TYPE AND WILDFIRE IN THE ALBERTA BOREAL MIXEDWOOD: WHAT DO FIRES BURN? , 2001 .

[20]  W. W. Miller,et al.  Wildfire effects on soil nutrients and leaching in a tahoe basin watershed. , 2006, Journal of environmental quality.

[21]  N. Nicholls,et al.  Interannual variations of area burnt in Tasmanian bushfires: relationships with climate and predictability , 2007 .

[22]  D. Mercer,et al.  Evaluating Alternative Prescribed Burning Policies to Reduce Net Economic Damages from Wildfire , 2007 .

[23]  J. Zêzere,et al.  Assessment and validation of wildfire susceptibility and hazard in Portugal , 2009 .

[24]  Futao Guo,et al.  What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests , 2016 .

[25]  Biswajeet Pradhan,et al.  A New Semiautomated Detection Mapping of Flood Extent From TerraSAR-X Satellite Image Using Rule-Based Classification and Taguchi Optimization Techniques , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Jan Hauke,et al.  Comparison of Values of Pearson's and Spearman's Correlation Coefficients on the Same Sets of Data , 2011 .

[27]  J. Miesel,et al.  Wildfire effects on soil properties in fire-prone pine ecosystems: Indicators of burn severity legacy over the medium term after fire , 2019, Applied Soil Ecology.

[28]  L. Ayalew,et al.  Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan , 2004 .

[29]  J. W. Kean,et al.  Estimating post-fire debris-flow hazards prior to wildfire using a statistical analysis of historical distributions of fire severity from remote sensing data , 2018 .

[30]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS , 2014 .

[31]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using integrated bivariate and multivariate statistical models , 2014, Environmental Earth Sciences.

[32]  Zohre Sadat Pourtaghi,et al.  Forest fire susceptibility mapping in the Minudasht forests, Golestan province, Iran , 2015, Environmental Earth Sciences.

[33]  K. Carlson,et al.  Effects of Wildfire on River Water Quality and Riverbed Sediment Phosphorus , 2015, Water, Air, & Soil Pollution.

[34]  P. Nyman,et al.  Wildfire effects on water quality in forest catchments: A review with implications for water supply , 2011 .

[35]  Pauline F. Grierson,et al.  Fire severity impacts on tree mortality and post-fire recruitment in tall eucalypt forests of southwest Australia , 2020 .

[36]  S. Stephens,et al.  The Effects of Forest Fuel-Reduction Treatments in the United States , 2012 .

[37]  Abbas Alimohammadi,et al.  A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping , 2010, Comput. Geosci..

[38]  Omid Rahmati,et al.  Spatial prediction of flood-susceptible areas using frequency ratio and maximum entropy models , 2018 .

[39]  Gary J. Sheridan,et al.  Quantifying the effects of topographic aspect on water content and temperature in fine surface fuel , 2015 .

[40]  Philip N. Omi,et al.  The use of shaded fuelbreaks in landscape fire management. , 2000 .

[41]  Christopher A. Hiemstra,et al.  Interactive effects of wildfire and climate on permafrost degradation in Alaskan lowland forests , 2015 .

[42]  B. Pradhan,et al.  Remote Sensing Data Derived Parameters and its Use in Landslide Susceptibility Assessment Using Shannon’s Entropy and GIS , 2012 .

[43]  A. Ozdemir,et al.  A comparative study of frequency ratio, weights of evidence and logistic regression methods for landslide susceptibility mapping: Sultan Mountains, SW Turkey , 2013 .

[44]  M. Obrist,et al.  Arthropod biodiversity after forest fires: winners and losers in the winter fire regime of the southern Alps , 2004 .

[45]  Dirk Van,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[46]  J. Keeley.  Fire intensity, fire severity and burn severity: a brief review and suggested usage , 2009 .

[47]  B. Pradhan,et al.  Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models , 2010 .

[48]  Biswajeet Pradhan,et al.  Spatial prediction of landslide hazards in Hoa Binh province (Vietnam): a comparative assessment of , 2012 .

[49]  Mark Crowley,et al.  A review of machine learning applications in wildfire science and management , 2020, Environmental Reviews.

[50]  J. Dupuy,et al.  Slope effect on laboratory fire spread: contribution of radiation and convection to fuel bed preheating , 2011 .

[51]  Ariel M. Aloe,et al.  Extracting the Variance Inflation Factor and Other Multicollinearity Diagnostics from Typical Regression Results , 2017 .

[52]  R. Heinsohn,et al.  Loss of habitat for a secondary cavity nesting bird after wildfire , 2016 .

[53]  A. Gill,et al.  The worldwide "wildfire" problem. , 2013, Ecological applications : a publication of the Ecological Society of America.

[54]  George Pallis,et al.  Use of unmanned vehicles in search and rescue operations in forest fires: advantages and limitations observed in a field trial , 2015 .

[55]  Mario Parise,et al.  Wildfire impacts on the processes that generate debris flows in burned watersheds , 2012, Natural Hazards.

[56]  Mustafa Neamah Jebur,et al.  Earthquake induced landslide susceptibility mapping using an integrated ensemble frequency ratio and logistic regression models in West Sumatera Province, Indonesia , 2014 .

[57]  D. Pamučar,et al.  Modeling the Spatial Variability of Forest Fire Susceptibility Using Geographical Information Systems and the Analytical Hierarchy Process , 2019, Spatial Modeling in GIS and R for Earth and Environmental Sciences.

[58]  Carlos Brun,et al.  Enhancing multi-model forest fire spread prediction by exploiting multi-core parallelism , 2014, The Journal of Supercomputing.

[59]  Domingos Xavier Viegas,et al.  Slope and wind effects on fire propagation , 2004 .

[60]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[61]  Marj Tonini,et al.  Space-time clustering analysis of wildfires: The influence of dataset characteristics, fire prevention policy decisions, weather and climate. , 2016, The Science of the total environment.

[62]  Yufeng Shi,et al.  Landslide Stability Analysis Based on Generalized Information Entropy , 2009, ESIAT.

[63]  C. J. West,et al.  Vegetation patterns, plant distribution and life forms across the alpine zone in southern Tierra del Fuego, Argentina , 2001 .

[64]  M. Yebra,et al.  The Vegetation Structure Perpendicular Index (VSPI): A forest condition index for wildfire predictions , 2019, Remote Sensing of Environment.

[65]  M. C. Kennedy,et al.  Fuel treatments and landform modify landscape patterns of burn severity in an extreme fire event. , 2014, Ecological applications : a publication of the Ecological Society of America.

[66]  E. Steel,et al.  Multi-Model Forecasts of Very-Large Fire Occurences during the End of the 21st Century , 2018, Climate.

[67]  Matthieu Kervyn,et al.  Thermal remote sensing of the low‐intensity carbonatite volcanism of Oldoinyo Lengai, Tanzania , 2008 .

[68]  Omid Ghorbanzadeh,et al.  Comparisons of Diverse Machine Learning Approaches for Wildfire Susceptibility Mapping , 2020, Symmetry.

[69]  N. Ueda,et al.  Application of Machine Learning Algorithms and Their Ensemble for Landslide Susceptibility Mapping , 2020, Understanding and Reducing Landslide Disaster Risk.

[70]  Hamid Reza Pourghasemi,et al.  Comparison of differences in resolution and sources of controlling factors for gully erosion susceptibility mapping , 2018, Geoderma.

[71]  M. Bednarik,et al.  Landslide susceptibility assessment using the bivariate statistical analysis and the index of entropy in the Sibiciu Basin (Romania) , 2011 .

[72]  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 .

[73]  D. Stow,et al.  Tracking MODIS NDVI time series to estimate fuel accumulation , 2015 .

[74]  Mustafa Neamah Jebur,et al.  Landslide susceptibility mapping using ensemble bivariate and multivariate statistical models in Fayfa area, Saudi Arabia , 2015, Environmental Earth Sciences.

[75]  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..

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

[77]  W. Covington,et al.  Toward reference conditions: wildfire effects on flora in an old-growth ponderosa pine forest , 2004 .

[78]  H. Rostamzadeh,et al.  Estimation of flood land use/land cover mapping by regional modelling of flood hazard at sub-basin level case study: Marand basin , 2019, Geomatics, Natural Hazards and Risk.

[79]  Xiaodong Li,et al.  Modeling Fire Spread Under Environmental Influence Using A Cellular Automation Approach , 2000 .

[80]  Biswajeet Pradhan,et al.  Fusion of Airborne LiDAR With Multispectral SPOT 5 Image for Enhancement of Feature Extraction Using Dempster–Shafer Theory , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[81]  R. Bradstock,et al.  NATIONAL FIRE DANGER RATING SYSTEM PROBABALISTIC FRAMEWORK PROJECT , 2014 .

[82]  W. Jolly,et al.  Modeling topographic influences on fuel moisture and fire danger in complex terrain to improve wildland fire management decision support , 2011 .

[83]  Carl N. Skinner,et al.  Basic principles of forest fuel reduction treatments , 2005 .

[84]  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.

[85]  Hamid Reza Pourghasemi,et al.  Landslide susceptibility modeling applying machine learning methods: A case study from Longju in the Three Gorges Reservoir area, China , 2018, Comput. Geosci..

[86]  Seyed Amir Naghibi,et al.  A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping , 2017 .

[87]  Himan Shahabi,et al.  Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability , 2019, Agricultural and Forest Meteorology.

[88]  Domingos Xavier Viegas,et al.  Fire spread in canyons , 2004 .

[89]  Bahareh Kalantar,et al.  Forest Fire Susceptibility Prediction Based on Machine Learning Models with Resampling Algorithms on Remote Sensing Data , 2020, Remote. Sens..

[90]  Francisco Martínez-Álvarez,et al.  A novel ensemble modeling approach for the spatial prediction of tropical forest fire susceptibility using LogitBoost machine learning classifier and multi-source geospatial data , 2018, Theoretical and Applied Climatology.

[91]  Sassan Saatchi,et al.  Estimation of Forest Fuel Load From Radar Remote Sensing , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[92]  A. Yalçın.  GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in Ardesen (Turkey): Comparisons of results and confirmations , 2008 .

[93]  Andrew L. Sullivan,et al.  Curvature effects in the dynamic propagation of wildfires , 2016 .

[94]  K. S. Reddy,et al.  Effect of wind speed and direction on convective heat losses from solar parabolic dish modified cavity receiver , 2016 .

[95]  S. Limin,et al.  Effects of agricultural land-use change and forest fire on N2O emission from tropical peatlands, Central Kalimantan, Indonesia , 2006 .

[96]  Javier Herrero,et al.  Topographic effects on solar radiation distribution in mountainous watersheds and their influence on reference evapotranspiration estimates at watershed scale. , 2010 .

[97]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[98]  Helmi Zulhaidi Mohd Shafri,et al.  Maximizing Urban Features Extraction from Multi-sensor Data with Dempster-Shafer Theory and HSI Data Fusion Techniques , 2015 .

[99]  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.

[100]  Klaus-Dieter Thoben,et al.  Machine learning in manufacturing: advantages, challenges, and applications , 2016 .

[101]  Alfian Abdul Halin,et al.  A COMPARISON BETWEEN THREE CONDITIONING FACTORS DATASET FOR LANDSLIDE PREDICTION IN THE SAJADROOD CATCHMENT OF IRAN , 2020 .

[102]  L. Ayalew,et al.  The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan , 2005 .

[103]  J. Sharples.  An overview of mountain meteorological effects relevant to fire behaviour and bushfire risk. , 2009 .

[104]  Biswajeet Pradhan,et al.  Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks , 2021, Geoscience Frontiers.

[105]  K. Itten,et al.  LIDAR-based geometric reconstruction of boreal type forest stands at single tree level for forest and wildland fire management , 2004 .

[106]  J. Vega,et al.  Spatially modeling wildland fire severity in pine forests of Galicia, Spain , 2017, European Journal of Forest Research.

[107]  Rina Grant-Biggs.  Flammable Australia: Fire Regimes, Biodiversity and Ecosystems in a Changing World , 2012 .

[108]  Saro Lee,et al.  Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data , 2005 .

[109]  Grant J. Williamson,et al.  Geographic Patterns of Fire Severity Following an Extreme Eucalyptus Forest Fire in Southern Australia: 2013 Forcett-Dunalley Fire , 2018, Fire.

[110]  Mário G. Pereira,et al.  Evolution of forest fires in Portugal: from spatio-temporal point events to smoothed density maps , 2017, Natural Hazards.

[111]  M. Flannigan,et al.  Fuel moisture sensitivity to temperature and precipitation: climate change implications , 2015, Climatic Change.

[112]  H. Pourghasemi,et al.  Landslide susceptibility mapping by binary logistic regression, analytical hierarchy process, and statistical index models and assessment of their performances , 2013, Natural Hazards.

[113]  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 .

[114]  Simon D. Jones,et al.  Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques , 2019, CATENA.

[115]  Aaron C. Greenville,et al.  Impact of 2019–2020 mega-fires on Australian fauna habitat , 2020, Nature Ecology & Evolution.

[116]  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.

[117]  R. O’Brien,et al.  A Caution Regarding Rules of Thumb for Variance Inflation Factors , 2007 .

[118]  H. Benjelloun,et al.  A Simple Technique to Estimate the Flammability Index of Moroccan Forest Fuels , 2011 .

[119]  Ahmed E. M. Al-Juaidi,et al.  Evaluation of flood susceptibility mapping using logistic regression and GIS conditioning factors , 2018, Arabian Journal of Geosciences.

[120]  Giorgos Mallinis,et al.  A data-driven approach to assess large fire size generation in Greece , 2017, Natural Hazards.

[121]  Lluís Brotons,et al.  Predictive modelling of fire occurrences from different fire spread patterns in Mediterranean landscapes , 2015 .

[122]  Albert Alvarez,et al.  Extreme Fire Severity Patterns in Topographic, Convective and Wind-Driven Historical Wildfires of Mediterranean Pine Forests , 2014, PloS one.