A Neural Network Model for Wildfire Scale Prediction Using Meteorological Factors

A forest fire is a natural disaster that destroys forest resources, thus having a severe impact on humans and on the animals and plants that depend on the forest environment. This paper presents a model for predicting the scale of forest wildfires of Alberta, Canada. A fire’s scale is determined by the combination of the fire’s duration and the size of the area it burns. Our prediction model enables fire rescuers to take appropriate measures to minimize damage caused by a wildfire based on its predicted scale in the fire’s early stages. The modeling data were collected from the Canada National Fire Database (CNFDB) published by Natural Resources Canada, which includes wildfire and meteorological data for Alberta, Canada. The size of the burned area and the fire’s duration were used to estimate the scale of a wildfire. After multi-collinearity testing and feature normalization, the data were divided into training and testing sets. Taking the meteorological factors as input values, a backpropagation neural network (BPNN), a recurrent neural network (RNN), and long short-term memory (LSTM) were implemented to establish prediction models. Of these classification methods, LSTM exhibited the highest accuracy, 90.9%. The results indicate that it is feasible to predict the scale of a forest wildfire at the beginning of its occurrence using meteorological information.

[1]  Florian Kraxner,et al.  Modeling Burned Areas in Indonesia: The FLAM Approach , 2018, Forests.

[2]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[3]  Tierui Zhang,et al.  Site-specific nucleation and growth kinetics in hierarchical nanosyntheses of branched ZnO crystallites. , 2006, Journal of the American Chemical Society.

[4]  Hermann Ney,et al.  From Feedforward to Recurrent LSTM Neural Networks for Language Modeling , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[5]  T. Swetnam,et al.  Landscape-scale controls over 20th century fire occurrence in two large Rocky Mountain (USA) wilderness areas , 2002, Landscape Ecology.

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

[7]  D. J. Rasbash.  Effects of fire on items which may have helped cause the fire , 1984 .

[8]  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.

[9]  A-Xing Zhu,et al.  Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution. , 2018, The Science of the total environment.

[10]  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.

[11]  Elif Derya Übeyli.  Combining recurrent neural networks with eigenvector methods for classification of ECG beats , 2009, Digit. Signal Process..

[12]  A. Mohammadzadeh,et al.  Fire Risk Assessment Using Neural Network and Logistic Regression , 2016, Journal of the Indian Society of Remote Sensing.

[13]  David L. Martell,et al.  A lightning fire occurrence model for Ontario , 2005 .

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

[15]  S. Anderson,et al.  Forest History: International Studies on Socioeconomic and Forest Ecosystem Change , 2000 .

[16]  Balbina Casas-Méndez,et al.  An Integer Linear Programming Model to Select and Temporally Allocate Resources for Fighting Forest Fires , 2018, Forests.

[17]  Meng Zhang,et al.  Non-Destructive Methodology to Determine Modulus of Elasticity in Static Bending of Quercus mongolica Using Near-Infrared Spectroscopy , 2018, Sensors.

[18]  Isaac C. Grenfell,et al.  Piloted ignition of live forest fuels , 2012 .

[19]  Wenhui Wang,et al.  Modeling Anthropogenic Fire Occurrence in the Boreal Forest of China Using Logistic Regression and Random Forests , 2016 .

[20]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[21]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[22]  Hua Li,et al.  [Influence of improved Kennard/Stone algorithm on the calibration transfer in near-infrared spectroscopy]. , 2011, Guang pu xue yu guang pu fen xi = Guang pu.

[23]  Yugang Niu,et al.  Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM , 2018 .

[24]  Gui-zhong Zhou,et al.  An evaluating model for smart growth plan based on BP neural network and set pair analysis , 2019, Journal of Cleaner Production.

[25]  Jürgen Schmidhuber,et al.  LSTM recurrent networks learn simple context-free and context-sensitive languages , 2001, IEEE Trans. Neural Networks.

[26]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[27]  Biswajeet Pradhan,et al.  Hybrid artificial intelligence approach based on neural fuzzy inference model and metaheuristic optimization for flood susceptibilitgy modeling in a high-frequency tropical cyclone area using GIS , 2016 .

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

[29]  Ai Sekizawa,et al.  Fire Risk Analysis: Its Validity And Potential For Application In Fire Safety , 2005 .

[30]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[31]  Eliot J. B. McIntire,et al.  Exploiting Poisson additivity to predict fire frequency from maps of fire weather and land cover in boreal forests of Québec, Canada , 2017 .

[32]  Jim Gould,et al.  Predicting the number of daily human-caused bushfires to assist suppression planning in south-west Western Australia , 2014 .

[33]  David R. Brillinger,et al.  Probability based models for estimation of wildfire risk , 2004 .

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

[35]  D. Nepstad,et al.  MODELING FOREST UNDERSTORY FIRES IN AN EASTERN AMAZONIAN LANDSCAPE , 2004 .

[36]  Jiaying Liu,et al.  Adaptive Batch Normalization for practical domain adaptation , 2018, Pattern Recognit..

[37]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[38]  Scott L. Goodrick,et al.  Forecasting intentional wildfires using temporal and spatiotemporal autocorrelations , 2012 .

[39]  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.

[40]  James A. Reggia,et al.  A generalized LSTM-like training algorithm for second-order recurrent neural networks , 2012, Neural Networks.

[41]  H. Nieto,et al.  Integration of Lightning- and Human-Caused Wildfire Occurrence Models , 2010 .