Forest Fire Susceptibility Modeling Using a Convolutional Neural Network for Yunnan Province of China

Abstract

Forest fires have caused considerable losses to ecologies, societies, and economies worldwide. To minimize these losses and reduce forest fires, modeling and predicting the occurrence of forest fires are meaningful because they can support forest fire prevention and management. In recent years, the convolutional neural network (CNN) has become an important state-of-the-art deep learning algorithm, and its implementation has enriched many fields. Therefore, we proposed a spatial prediction model for forest fire susceptibility using a CNN. Past forest fire locations in Yunnan Province, China, from 2002 to 2010, and a set of 14 forest fire influencing factors were mapped using a geographic information system. Oversampling was applied to eliminate the class imbalance, and proportional stratified sampling was used to construct the training/validation sample libraries. A CNN architecture that is suitable for the prediction of forest fire susceptibility was designed and hyperparameters were optimized to improve the prediction accuracy. Then, the test dataset was fed into the trained model to construct the spatial prediction map of forest fire susceptibility in Yunnan Province. Finally, the prediction performance of the proposed model was assessed using several statistical measures—Wilcoxon signed-rank test, receiver operating characteristic curve, and area under the curve (AUC). The results confirmed the higher accuracy of the proposed CNN model (AUC 0.86) than those of the random forests, support vector machine, multilayer perceptron neural network, and kernel logistic regression benchmark classifiers. The CNN has stronger fitting and classification abilities and can make full use of neighborhood information, which is a promising alternative for the spatial prediction of forest fire susceptibility. This research extends the application of CNN to the prediction of forest fire susceptibility.

Keywords

China / Convolutional neural network / Forest fire susceptibility / Geographic information system / Machine learning

References

[1] Adab H, Kanniah KD, Solaimani K. Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques. Natural Hazards, 2013, 65(3): 1723-1743

[2] Arpaci A, Malowerschnig B, Sass O, Vacik H. Using multi variate data mining techniques for estimating fire susceptibility of Tyrolean forests. Applied Geography, 2014, 53: 258-270

[3] Bajocco S, Dragoz E, Gitas I, Smiraglia D, Salvati L, Ricotta C. Mapping forest fuels through vegetation phenology: The role of coarse-resolution satellite time-series. PLoS ONE, 2015, 10(3): 1-14

[4] Bar Massada A, Syphard AD, Stewart SI, Radeloff VC. Wildfire ignition-distribution modelling: a comparative study in the Huron-Manistee National Forest, Michigan, USA. International Journal of Wildland Fire, 2013, 22(2): 174-183

[5] Bergstra J, Bengio Y. Random search for hyper-parameter optimization. Journal of Machine Learning Research, 2012, 13(1): 281-305.

[6] Bisquert M, Caselles E, Sánchez JM, Caselles V. Application of artificial neural networks and logistic regression to the prediction of forest fire danger in Galicia using MODIS data. International Journal of Wildland Fire, 2012, 21(8): 1025-1029

[7] Buda M, Maki A, Mazurowski MA. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 2018, 106: 249-259

[8] Bui DT, Le KTT, Nguyen VC, Le HD, Revhaug I. Tropical forest fire susceptibility mapping at the Cat Ba National Park area, Hai Phong City, Vietnam, using GIS-based Kernel logistic regression. Remote Sensing, 2016, 8(4): 1-15.

[9] Bui DT, Tuan TA, Klempe H, Pradhan B, Revhaug I. 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. Landslides, 2016, 13(2): 361-378

[10] Cao Y, Wang M, Liu K. Wildfire susceptibility assessment in Southern China: A comparison of multiple methods. International Journal of Disaster Risk Science, 2017, 8(2): 164-181

[11] Colkesen I, Sahin EK, Kavzoglu T. Susceptibility mapping of shallow landslides using kernel-based Gaussian process, support vector machines and logistic regression. Journal of African Earth Sciences, 2016, 118: 53-64

[12] Crimmins MA. Synoptic climatology of extreme fire-weather conditions across the southwest United States. International Journal of Climatology, 2006, 26(8): 1001-1016

[13] Dash M, Liu H. Feature selection for classification. Intelligent Data Analysis, 1997, 1(1–4): 131-156

[14] Dimuccio LA, Ferreira R, Cunha L, Campar de Almeida A. Regional forest-fire susceptibility analysis in central Portugal using a probabilistic ratings procedure and artificial neural network weights assignment. International Journal of Wildland Fire, 2011, 20(6): 776-791

[15] Elmas Ç, Sönmez Y. A data fusion framework with novel hybrid algorithm for multi-agent Decision Support System for Forest Fire. Expert Systems with Applications, 2011, 38(8): 9225-9236

[16] Freeman EA, Moisen GG. A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and kappa. Ecological Modelling, 2008, 217(1): 48-58

[17] Guo F, Su Z, Wang G, Sun L, Lin F, Liu A. Wildfire ignition in the forests of southeast China: Identifying drivers and spatial distribution to predict wildfire likelihood. Applied Geography, 2016, 66: 12-21

[18] Hantson S, Pueyo S, Chuvieco E. Global fire size distribution is driven by human impact and climate. Global Ecology and Biogeography, 2015, 24(1): 77-86

[19] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507

[20] Hong H, Jaafari A, Zenner EK. Predicting spatial patterns of wildfire susceptibility in the Huichang County, China: An integrated model to analysis of landscape indicators. Ecological Indicators, 2019, 101: 878-891

[21] Hong H, Pradhan B, Xu C, Tien Bui D. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines. Catena, 2015, 133: 266-281

[22] Hong H, Tsangaratos P, Ilia I, Liu J, Zhu AX, Xu C. 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. Science of the Total Environment, 2018, 630: 1044-1056

[23] Hu F, Xia GS, Hu J, Zhang L. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing, 2015, 7(11): 14680-14707

[24] Jaafari A, Zenner EK, Panahi M, Shahabi H. Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability. Agricultural and Forest Meteorology, 2019, 266–267: 198-207

[25] Jaafari A, Zenner EK, Pham BT. Wildfire spatial pattern analysis in the Zagros Mountains, Iran: A comparative study of decision tree based classifiers. Ecological Informatics, 2018, 43: 200-211

[26] Kim, S.J., C.H. Lim, G.S. Kim, J. Lee, T. Geiger, O. Rahmati, Y. Son, and W.K. Lee. 2019. Multi-temporal analysis of forest fire probability using socio-economic and environmental variables. Remote Sensing 11(1): Article 86.

[27] Kingma, D.P., and J. Ba. 2014. Adam: A method for stochastic optimization. Presented as a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015. arXiv preprint abs:1412.6980. Ithaca, NY: Cornell University.

[28] Krizhevsky, A., I. Sutskever, G.E. Hinton. 2013. ImageNet classification with deep convolutional neural networks. In Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS), 3–6 December 2012, Lake Tahoe, Nevada, USA, ed. F. Pereira, C.J.C. Burges, L. Bottou, and K.Q. Weinberger, Vol. 2, 1097–1105.

[29] Lecun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444

[30] Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of IEEE, 1998, 86(11): 2278-2324

[31] Leuenberger M, Parente J, Tonini M, Pereira MG, Kanevski M. Wildfire susceptibility mapping: Deterministic vs. stochastic approaches. Environmental Modelling and Software, 2018, 101: 194-203

[32] Liu T, Abd-Elrahman A. Deep convolutional neural network training enrichment using multi-view object-based analysis of Unmanned Aerial systems imagery for wetlands classification. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 139: 154-170

[33] López V, Fernández A, García S, Palade V, Herrera F. An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Information Sciences, 2013, 250: 113-141

[34] Moritz, M. A., M.-A. Parisien, E. Batllori, M. A. Krawchuk, J. Van Dorn, D.J. Ganz, and K. Hayhoe. 2012. Climate change and disruptions to global fire activity. Ecosphere 3(6): Article 49.

[35] Muhammad, K., J. Ahmad, and S.W. Baik. 2018. Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing 288(C): 30–42.

[36] Ngoc Thach N, Bao-Toan Ngo D, Xuan-Canh P, Hong-Thi N, Hang Thi B, Nhat-Duc H, Dieu TB. Spatial pattern assessment of tropical forest fire danger at Thuan Chau area (Vietnam) using GIS-based advanced machine learning algorithms: A comparative study. Ecological Informatics, 2018, 46: 74-85

[37] O’Brien RM. A caution regarding rules of thumb for variance inflation factors. Quality and Quantity, 2007, 41(5): 673-690

[38] Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira JMC. Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest. Forest Ecology and Management, 2012, 275: 117-129

[39] Pew KL, Larsen CPS. GIS analysis of spatial and temporal patterns of human-caused wildfires in the temperate rain forest of Vancouver Island. Canada. Forest Ecology and Management, 2001, 140(1): 1-18

[40] Pourtaghi ZS, Pourghasemi HR, Aretano R, Semeraro T. Investigation of general indicators influencing on forest fire and its susceptibility modeling using different data mining techniques. Ecological Indicators, 2016, 64: 72-84

[41] Renard Q, Ṕlissier R, Ramesh BR, Kodandapani N. Environmental susceptibility model for predicting forest fire occurrence in the Western Ghats of India. International Journal of Wildland Fire, 2012, 21(4): 368-379

[42] Running SW. Is global warming causing more, larger wildfires?. Science, 2006, 313(5789): 927-928

[43] Sachdeva S, Bhatia T, Verma AK. GIS-based evolutionary optimized Gradient Boosted Decision Trees for forest fire susceptibility mapping. Natural Hazards, 2018, 92(3): 1399-1418

[44] Satir O, Berberoglu S, Donmez C. Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem. Geomatics, Natural Hazards and Risk, 2016, 7(5): 1645-1658

[45] Schmidhuber J. Deep Learning in neural networks: An overview. Neural Networks, 2015, 61: 85-117

[46] Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Information Processing and Management, 2009, 45(4): 427-437

[47] Tien Bui D, Bui QT, Nguyen QP, Pradhan B, Nampak H, Trinh PT. 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. Agricultural and Forest Meteorology, 2017, 233: 32-44

[48] Tien Bui D, Hoang ND, Samui P. Spatial pattern analysis and prediction of forest fire using new machine learning approach of Multivariate Adaptive Regression Splines and Differential Flower Pollination optimization: A case study at Lao Cai province (Viet Nam). Journal of Environmental Management, 2019, 237: 476-487

[49] Tobler WR. A computer movie simulating urban growth in the Detroit region. Economic Geography, 1970, 46(sup1): 234-240

[50] de Vasconcelos MJP, Silva S, Tomé M, Alvim M, Perelra JMC. Spatial Prediction of Fire Ignition Probabilities: Comparing Logistic Regression and Neural Networks. Photogrammetric Engineering & Remote Sensing, 2001, 67(1): 73-81.

[51] Vetrivel A, Gerke M, Kerle N, Nex F, Vosselman G. Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learning. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 140: 45-59

[52] Wang Y, Fang Z, Hong H. Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China. Science of the Total Environment, 2019, 666: 975-993

[53] Wilcoxon F. Individual comparisons by ranking methods. Biometrics Bulletin, 1945, 1(6): 80-83

[54] Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: An overview and application in radiology. Insights into Imaging, 2018, 9(4): 611-629

[55] Yi K, Tani H, Zhang J, Guo M, Wang X, Zhong G. Long-term satellite detection of post-fire vegetation trends in boreal forests of China. Remote Sensing, 2013, 5(12): 6938-6957

[56] Ying L, Han J, Du Y, Shen Z. Forest fire characteristics in China: Spatial patterns and determinants with thresholds. Forest Ecology and Management, 2018, 424: 345-354

[57] Zhang X. Vegetation map of the People’s Republic of China (1:1000000), 2007, Beijing: Geology Press (in Chinese)

[58] Zhang C, Pan X, Li H, Gardiner A, Sargent I, Hare J, Atkinson PM. A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 140: 133-144