GIS-based spatial prediction of tropical forest fire danger using a new hybrid machine learning method

Abstract Forest fire danger map at regional scale is considered of utmost importance for local authority to efficiently allocate its resources to fire prevention measures and establish appropriate land use plans. This study aims at introduce a new machine learning method, named as DFP-MnBpAnn, based on Artificial Neural Network (Ann) with a novel hybrid training algorithm of Differential Flower Pollination (DFP) and mini-match backpropagation (MnBp) for spatial modeling of forest fire danger. Tropical forest of the Lam Dong province (Vietnam) was used as case study. To achieve this task, a Geographical Information System (GIS) database of the forest fire for the study area was established. Accordingly, DFP, as a metaheuristic method, is used to optimize the weights and structure of Ann to fit the GIS database at hand. Whereas, MnBp is employed periodically during the DFP-based optimization process, in which MnBp acts as a local search aiming to accelerate both the quality of the found solutions and the convergence rate. Experimental outcomes demonstrate that the proposed DFP-MnBpAnn model is superior to other benchmark methods with satisfactory prediction accuracy (Classification Accuracy Rate = 88.43%). This fact confirms that DFP-MnBpAnn is a promising alternative for the problem of large-scale forest fire danger mapping.

[1]  Khawaja M. Asim,et al.  Earthquake magnitude prediction in Hindukush region using machine learning techniques , 2016, Natural Hazards.

[2]  Nhat-Duc Hoang,et al.  GIS-Based Landslide Spatial Modeling Using Batch-Training Back-propagation Artificial Neural Network: A Study of Model Parameters , 2017 .

[3]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[4]  Khalil Taheri,et al.  A hybrid artificial bee colony algorithm-artificial neural network for forecasting the blast-produced ground vibration , 2016, Engineering with Computers.

[5]  Cheng Liu,et al.  Detection, Emission Estimation and Risk Prediction of Forest Fires in China Using Satellite Sensors and Simulation Models in the Past Three Decades—An Overview , 2011, International journal of environmental research and public health.

[6]  Goutam Saha,et al.  Large-Scale Recurrent Neural Network Based Modelling of Gene Regulatory Network Using Cuckoo Search-Flower Pollination Algorithm , 2016, Adv. Bioinformatics.

[7]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[8]  Nhat-Duc Hoang,et al.  Spatial prediction of rainfall-induced shallow landslides using hybrid integration approach of Least-Squares Support Vector Machines and differential evolution optimization: a case study in Central Vietnam , 2016, Int. J. Digit. Earth.

[9]  Andrew Lewis,et al.  Let a biogeography-based optimizer train your Multi-Layer Perceptron , 2014, Inf. Sci..

[10]  Nhat-Duc Hoang,et al.  Predicting Colonization Growth of Algae on Mortar Surface with Artificial Neural Network , 2016, J. Comput. Civ. Eng..

[11]  Kang-Tsung Chang,et al.  Modelling the spatial variability of wildfire susceptibility in Honduras using remote sensing and geographical information systems , 2017 .

[12]  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.

[13]  Lia Duarte,et al.  Forest fire risk maps: a GIS open source application – a case study in Norwest of Portugal , 2013, Int. J. Geogr. Inf. Sci..

[14]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[15]  Nhat-Duc Hoang,et al.  Groutability estimation of grouting processes with cement grouts using Differential Flower Pollination Optimized Support Vector Machine , 2016, Appl. Soft Comput..

[16]  B. Pham,et al.  Bagging based Support Vector Machines for spatial prediction of landslides , 2018, Environmental Earth Sciences.

[17]  Adam P. Piotrowski,et al.  Differential Evolution algorithms applied to Neural Network training suffer from stagnation , 2014, Appl. Soft Comput..

[18]  Benjamin Koetz,et al.  Multi-source land cover classification for forest fire management based on imaging spectrometry and LiDAR data , 2008 .

[19]  Francisco Martínez-Álvarez,et al.  Earthquake magnitude prediction based on artificial neural networks: A survey , 2016 .

[20]  Wei Chen,et al.  Land Subsidence Susceptibility Mapping in South Korea Using Machine Learning Algorithms , 2018, Sensors.

[21]  Zhong Zheng,et al.  Forest fire spread simulating model using cellular automaton with extreme learning machine , 2017 .

[22]  Christos Polykretis,et al.  Comparison and evaluation of landslide susceptibility maps obtained from weight of evidence, logistic regression, and artificial neural network models , 2018, Natural Hazards.

[23]  Tao Chen,et al.  Back propagation neural network with adaptive differential evolution algorithm for time series forecasting , 2015, Expert Syst. Appl..

[24]  H. Khanna Nehemiah,et al.  Neural network classifier optimization using Differential Evolution with Global Information and Back Propagation algorithm for clinical datasets , 2016, Appl. Soft Comput..

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

[26]  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.

[27]  Masoud Monjezi,et al.  Blast-induced air and ground vibration prediction: a particle swarm optimization-based artificial neural network approach , 2015, Environmental Earth Sciences.

[28]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[29]  Evan R. DeLancey,et al.  The spatially varying influence of humans on fire probability in North America , 2016 .

[30]  Nhat-Duc Hoang,et al.  Predicting earthquake-induced soil liquefaction based on a hybridization of kernel Fisher discriminant analysis and a least squares support vector machine: a multi-dataset study , 2018, Bulletin of Engineering Geology and the Environment.

[31]  Salwani Abdullah,et al.  Optimization of neural network using kidney-inspired algorithm with control of filtration rate and chaotic map for real-world rainfall forecasting , 2018, Eng. Appl. Artif. Intell..

[32]  Nhat-Duc Hoang,et al.  Enhancing the accuracy of rainfall-induced landslide prediction along mountain roads with a GIS-based random forest classifier , 2019, Bulletin of Engineering Geology and the Environment.

[33]  V. Caselles,et al.  Application of artificial neural networks and logistic regression to the prediction of forest fire danger in Galicia using MODIS data , 2012 .

[34]  Jatinder N. D. Gupta,et al.  Comparative evaluation of genetic algorithm and backpropagation for training neural networks , 2000, Inf. Sci..

[35]  Huadong Guo,et al.  Assessing the impact of climatic parameters and their inter-annual seasonal variability on fire activity using time series satellite products in South China (2001–2014) , 2017, Natural Hazards.

[36]  Alicia Troncoso Lora,et al.  Medium–large earthquake magnitude prediction in Tokyo with artificial neural networks , 2015, Neural Computing and Applications.

[37]  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.

[38]  P. Pattynama,et al.  Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. , 1998, European journal of radiology.

[39]  S. Berberoglu,et al.  Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem , 2016 .

[40]  Xin-She Yang,et al.  Flower Pollination Algorithm for Global Optimization , 2012, UCNC.

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

[42]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

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

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

[45]  Francisco Martínez-Álvarez,et al.  Determining the best set of seismicity indicators to predict earthquakes. Two case studies: Chile and the Iberian Peninsula , 2013, Knowl. Based Syst..

[46]  D. Riaño,et al.  Multitemporal Modelling of Socio-Economic Wildfire Drivers in Central Spain between the 1980s and the 2000s: Comparing Generalized Linear Models to Machine Learning Algorithms , 2016, PloS one.

[47]  Bulent Tutmez,et al.  Mapping forest fires by nonparametric clustering analysis , 2017, Journal of Forestry Research.

[48]  Dieu Tien Bui,et al.  Spatial pattern assessment of tropical forest fire danger at Thuan Chau area (Vietnam) using GIS-based advanced machine learning algorithms: A comparative study , 2018, Ecol. Informatics.

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

[50]  Adam P. Piotrowski,et al.  Optimizing neural networks for river flow forecasting – Evolutionary Computation methods versus the Levenberg–Marquardt approach , 2011 .

[51]  Onur Satir,et al.  Monitoring the land use/cover changes and habitat quality using Landsat dataset and landscape metrics under the immigration effect in subalpine eastern Turkey , 2016, Environmental Earth Sciences.

[52]  Tarek Hegazy,et al.  Developing Practical Neural Network Applications Using Back‐Propagation , 1994 .

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

[54]  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 .

[55]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[56]  José Augusto Baranauskas,et al.  How Many Trees in a Random Forest? , 2012, MLDM.

[57]  Weibin You,et al.  Geographical information system-based forest fire risk assessment integrating national forest inventory data and analysis of its spatiotemporal variability , 2017 .

[58]  Jeff Heaton,et al.  Introduction to neural networks for C , 2008 .

[59]  Biswajeet Pradhan,et al.  Forest fire susceptibility and risk mapping using remote sensing and geographical information systems (GIS) , 2007 .

[60]  Saeedeh Eskandari,et al.  A new approach for forest fire risk modeling using fuzzy AHP and GIS in Hyrcanian forests of Iran , 2017, Arabian Journal of Geosciences.