Regional forest-fire susceptibility analysis in central Portugal using a probabilistic ratings procedure and artificial neural network weights assignment

Geographic information system analysis and artificial neural network modelling were combined to evaluate forest-fire susceptibility in the Central Portugal administrative area. Data on forest fire events, indicated by burnt areas during the years from 1990 to 2007, were identified from official records. Topographic, supporting infrastructures, vegetation cover, climatic, demographic and satellite-image data were collected, processed and integrated into a spatial database using geographic information system techniques. Eight fire-related factors were extracted from the collected data, including topographic slope and aspect, road density, viewsheds from fire watchtowers, land cover, Landsat Normalised Difference Vegetation Index, precipitation and population density. Ratings were calculated for the classes or categories of each factor using a frequency-probabilistic procedure. The thematic layers (burnt areas and fire-related factors) were analysed using an advanced artificial neural network model to calculate the relative weight of each factor in explaining the distribution of burnt areas. A forest-fire susceptibility index was calculated using the trained back-propagation artificial neural network weights and the frequency-probabilistic ratings, and then a general forest-fire susceptibility index map was constructed in geographic information system. Burnt areas were used to evaluate the forest-fire susceptibility index map, and the results showed an agreement of 78%. This forest-fire susceptibility map can be used in strategic and operational forest-fire management planning at the regional scale.

[1]  Brian G. Lees,et al.  Neural network applications in the geosciences: An introduction , 1996 .

[2]  Saro Lee,et al.  Determination and application of the weights for landslide susceptibility mapping using an artificial neural network , 2004 .

[3]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[4]  J. R. Jensen.  Remote Sensing of the Environment: An Earth Resource Perspective , 2000 .

[5]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

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

[7]  R. Lunetta,et al.  A change detection experiment using vegetation indices. , 1998 .

[8]  E. Schanda,et al.  Remote sensing of the environment , 1978, Naturwissenschaften.

[9]  Mika Siljander,et al.  Predictive fire occurrence modelling to improve burned area estimation at a regional scale: A case study in East Caprivi, Namibia , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[10]  M. S. Moran,et al.  Evaluation of simplified procedures for retrieval of land surface reflectance factors from satellite sensor output , 1992 .

[11]  L. Ermini,et al.  Artificial Neural Networks applied to landslide susceptibility assessment , 2005 .

[12]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[13]  M. R. Brown,et al.  Neural network and GA approaches for dwelling fire occurrence prediction , 2006, Knowl. Based Syst..

[14]  F. Moreira,et al.  Regional variations in wildfire susceptibility of land-cover types in Portugal: implications for landscape management to minimize fire hazard , 2009 .

[15]  Fernando Pérez-Cabello,et al.  Mapping lightning/human-caused wildfires occurrence under ignition point location uncertainty , 2007 .

[16]  M. J. Pereira,et al.  Assessing spatial uncertainty of the Portuguese fire risk through direct sequential simulation , 2010 .

[17]  Saro Lee,et al.  Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea , 2007 .

[18]  P. McCullagh,et al.  Generalized Linear Models, 2nd Edn. , 1990 .

[19]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[20]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[21]  F. J. Lozano,et al.  A multi-scale approach for modeling fire occurrence probability using satellite data and classification trees: A case study in a mountainous Mediterranean region , 2008 .

[22]  Yosio Edemir Shimabukuro,et al.  Predicting forest fire in the Brazilian Amazon using MODIS imagery and artificial neural networks , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[23]  P. Gong,et al.  Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping , 1996 .

[24]  A. Fernández,et al.  Temporal evolution of the NDVI as an indicator of forest fire danger , 1996 .

[25]  M. Ramos,et al.  Ground temperature regimes and geomorphological implications in a Mediterranean mountain (Serra da Estrela, Portugal) , 2003 .

[26]  F. Maselli.  Use of NOAA-AVHRR NDVI images for the estimation of dynamic fire risk in Mediterranean areas , 2003 .

[27]  M. Vasconcelos,et al.  Spatial Prediction of Fire Ignition Probabilities: Comparing Logistic Regression and Neural Networks , 2001 .

[28]  F. Rego.  lAND USE CHANGES AND WILDFIRES , 1992 .

[29]  J. Beverly,et al.  Modeling fire susceptibility in west central Alberta, Canada , 2009 .

[30]  S. López,et al.  An evaluation of the utility of NOAA AVHRR images for monitoring forest fire risk in Spain , 1991 .

[31]  Martin T. Hagan,et al.  Neural network design , 1995 .

[32]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[33]  Rajarshi Guha,et al.  Interpreting Computational Neural Network Quantitative Structure-Activity Relationship Models: A Detailed Interpretation of the Weights and Biases , 2005, J. Chem. Inf. Model..

[34]  E. Chuvieco,et al.  Application of remote sensing and geographic information systems to forest fire hazard mapping. , 1989 .

[35]  José M. C. Pereira,et al.  Atmospheric conditions associated with the exceptional fire season of 2003 in Portugal , 2006 .

[36]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[37]  Luciano Lourenço.  “Perigos” das “Cartas de risco”: comentários ao modelo proposto no Guia Técnico para Elaboração do PMDFCI , 2008 .

[38]  Manoj K. Arora,et al.  A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas , 2006 .

[39]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[40]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[41]  Joong-Sun Won,et al.  The Application of Artificial Neural Networks to Landslide Susceptibility Mapping at Janghung, Korea , 2006 .

[42]  Kostas Kalabokidis,et al.  Integrating new methods and tools in fire danger rating , 2007 .

[43]  D. Varnes.  Landslide hazard zonation: A review of principles and practice , 1984 .

[44]  Pradhan Biswajeet,et al.  Utilization of Optical Remote Sensing Data and GIS Tools for Regional Landslide Hazard Analysis Using an Artificial Neural Network Model , 2007 .

[45]  Anuradha Eaturu,et al.  Spatial Distribution of Forest Fires and Controlling Factors in Andhra Pradesh, India Using Spot Satellite Datasets , 2006, Environmental monitoring and assessment.

[46]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[47]  Giovanni Bovio,et al.  Comparative study of various methods of fire danger evaluation in southern Europe , 1994 .

[48]  Dx Viegas.  Some Thoughts on the Wind and Slope Effects on Fire Propagation , 1994 .

[49]  Serge Rambal,et al.  Some determinants of the spatio-temporal fire cycle in a mediterranean landscape (Corsica, France) , 2003, Landscape Ecology.

[50]  S. Dasgupta,et al.  Design of a susceptibility index for fire risk monitoring , 2006, IEEE Geoscience and Remote Sensing Letters.

[51]  Lefteri H. Tsoukalas,et al.  Fuzzy and neural approaches in engineering , 1997 .

[52]  Sue Ellen Haupt,et al.  Artificial Intelligence Methods in the Environmental Sciences , 2008 .

[53]  Weiguo Song,et al.  Artificial neural network approach for modeling the impact of population density and weather parameters on forest fire risk , 2009 .

[54]  Barak A. Pearlmutter,et al.  Equivalence Proofs for Multi-Layer Perceptron Classifiers and the Bayesian Discriminant Function , 1991 .

[55]  Josep Piñol,et al.  Climate Warming, Wildfire Hazard, and Wildfire Occurrence in Coastal Eastern Spain , 1998 .

[56]  William J. Ripple,et al.  The role of terrain in a fire mosaic of a temperate coniferous forest , 1997 .

[57]  P. Chavez.  Image-Based Atmospheric Corrections - Revisited and Improved , 1996 .

[58]  D. Collett.  Modelling Binary Data , 1991 .

[59]  E. Chuvieco,et al.  Assessment of forest fire danger conditions in southern Spain from NOAA images and meteorological indices , 2003 .

[60]  Saro Lee,et al.  Landslide susceptibility analysis using GIS and artificial neural network , 2003 .

[61]  Steven Haberman,et al.  Generalized linear models and actuarial science , 1996 .

[62]  Nairanjana Dasgupta,et al.  Land Cover Type and Fire in Portugal: Do Fires Burn Land Cover Selectively? , 2005, Landscape Ecology.

[63]  Keith M. Reynolds,et al.  A method for mapping fire hazard and risk across multiple scales and its application in fire management. , 2010 .

[64]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

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

[66]  H. Anderson.  Aids to Determining Fuel Models for Estimating Fire Behavior , 1982 .

[67]  António de Brum Ferreira,et al.  Novas observações acerca da glaciação da Serra da Estrela , 1997 .

[68]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[69]  Weiyang Zhou,et al.  Verification of the nonparametric characteristics of backpropagation neural networks for image classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[70]  J. Jeffers,et al.  Responses of Forest Ecosystems to Environmental Changes , 1992, Springer Netherlands.

[71]  Juli G. Pausas.  Changes in Fire and Climate in the Eastern Iberian Peninsula (Mediterranean Basin) , 2004 .

[72]  Robert A. Schowengerdt,et al.  A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery , 1995 .