Determination of the effective criteria of forest fire occurrence by using GIS and ANN (Case study: Golestan province)

Document Type : Complete scientific research article

Authors

Abstract

Forest fire management has important role in fire prevention and effects. The aim of this study was applied of Geographical Information System(GIS) and Artificial Neural Network (ANN) to determine forest fire criteria in Golestan province. The influence of each parameter on fire ignition was determined by collecting of 37 sample from burned area and 37 sample from not burned area. For formation network between criteria and fire occurrence used of Multilayer perceptron (MLP) with Hyperbolic Pattern Algorithms. the results shown raining and distance from road had must influence on forest fire ignition. Validation test showed that the best network obtained in run 4 and epoch 450 with 0.0038 Final Mean Square Error (FMSE) in training steps. Also, about 95 percent of area burned and 84 of unburned areas has been properly classified. Finally, forest fire hazard maps was obtained based on each criteria weights. Result showed this network with 2 hidden layer and 12 neuron in each of them has best accuracy, and correlation coefficient (R) was 0.80.

Keywords

Main Subjects


1. Aleemahmoodi, S.S., Feghhi, J., and Jabbarian, A.B. 2013. Predicting the Occurrence of
Natural Fires in Forests and Ranges using Artificial Neural Networks (Case Study: Zagros
Region, Izeh county). Esfehan, J. Applyed Ecology., 1: 2. 75-86. (in persian)
2. Aleemahmoodi, S.S., Feghhi, J., Jabbarian, A.B., Danehkar, A., and Attarod, P. 2013.
Applying the Regression Models to Assess the Influences of Climate Factors on Forest Fires
(Case Study: Izeh). Tehran, J. Nat. Rec., 2: 66. 191-201. (in Persian)
3. Bernabeuet, P., Vergara, L., Bosh, I., and Igual, J. 2004. A prediction/detection scheme for
automatic forest fire surveillance. Dig. Sig. Proc., J. 14: 5. 481-507.
4. Chuvieco, E., and Congalton, R.G. 1989. Application of remote sensing and geographic
information system to forest fire hazard mapping. Remote Sensing Environment, 29(2): 147-
159.
5. Daneshrad, A. 2006. Effect of forest degridation on desease. J. publicated in Zitoon., 54(8):
(in persian)
6. Dong, XU., Shao, G., Limin, D., Zhanqing, H, Lei, T., and Hui, W. 2005. Forest fire risk
zone mapping from satellite GIS FORE Baihe Forestry Bureau, Jilin, China. Fores. Search. J.
16: 3.169-174.
7. Eduardo, E.M., Gustavo, F.B.A., Petri, K.E.P., and Yosio, E.Sh. 2011. Fire risk assessment
in the Brazilian Amazon using MODIS imagery and change vector analysis. Applied
Geography J. 31: 1. 76-84.
8. Elmas, C., and Sonmez, Y. 2011. A data fusion framework with novel hybrid algorithm for
multi-agent. Decision Support System for Forest Fire Cetin. Expert Systems with
Applications J. 38: 8. 9225-9236.
9. Ertena, E., Kurgun, V., and Musaoglue, N. 2004. Forest fire risk zone mapping from satellite
imagery and GIS: a case study. XXth Congress of the International Society for
Photogrammetry and Remote Sensing, Istanbul. Turkey: 222-230.
10. FAO. 2009. The State of the World’s Forests 2009. Food and Agriculture Organization of
the United Nations, Rome.
11. Golestan province's water resources. 2013. http://hamidrezadeylam.blogfa.com/post/9.
12. Gortmaker, K. 2011. Forest fire hazard mapping in the LaPeyne area. France. Faculty of
Geosciences Theses. 61p.
13. Hernandez, P., Arbelo, M., and Gonzalez, A. 2006. Fire risk assessment using satellite data.
Advances in space research J. 37: 4. 741- 746.
14. Huyen, D.T., Th., and Tuan, V.A. 2008. Applying GIS and Multi Criteria Evaluation in
Forest Fire Risk Zoning in Sona La Province, Vietnam. International Symposium on
Geoinformatics for Spatial Infrastructure Development in Earth and Allied Sciences. Iran
Meteorological Organization. (In Persian)
15. Jaiswal, R.K., Saumitra, M., Kumaran, R.D., Rajesh, S. 2002. Forest fire risk zone mapping
from satellite imagery and GIS. International Journal of Applied Earth Observation and
Geoinformation. 4: 1–10
16. Kia, M. 2009. Neural network in Matlab. Publicated by nshre Kian Rayane Sabz. 226p. (in
Persian)
17. Mohamadi, F., SHabanian, M., Poorhashmi, M., and Fatehi, P. 2009. Forest fire risk
mapping using GIS and AHP in DA part of the forest. Kordestan, J. Quarterly Iran. Forest
Pop. Res., 18: 4. 569-586. (in Persian)
18. Sarkargar, ardakani, A., Valdan, Zoj, M., and Mansourian, A. 2009. Spatial analysis of fire
using RS, GIS in different parts of the country. Tehran, J. Ecology. 35: 52. 25- 34. (In
Persian)
19. Sebastian, S. 2002. Multi perceptreon and back propagation learning, 9.641
Lecture4.September. Doi=10.1.1.86.8968.
20. Somashekar, R., Ravikumar, P., Mohankumar, C., Prakash, K., and Nagaraja, B. 2009. Burnt
area mapping of bandipur national park, India using IRS1C 1D LISS III data. Indiansoc
Remote sensing J. 37: 37- 50.
21. Vasilakos, C., Kalabokidis, K., Hatzopoulos, J., and Matsinos, I. 2009. Identifying wildland
fire ignition factors through sensitivity analysis of a neural network. Natural Hazards J.
50:1.125-143.DOI 10.1007/s11069-008-9326-3.
22. Yang, L., Dawson, C., Brown, M., and Gell, M. 2006. Neural network and GA approaches
for dwelling fire occurrence prediction. Knowledge-Based Systems J. 19: 4. 213-
219.Doi:10.1016/j.knosys.2005.11.021.
23. Yuan, H. 2002. Development and evaluation of advanced data for accurate Land-us/Landcover
mapping, Phd Thesis, Departement of Forestry, North Carolina StateUniversity.
repository.lib.ncsu.edu/ir/bitstream/1840.16/3829/1/etd.pdf.
24. Zumbrunnen, T., Pezzatti, G., Menéndez, P., Bugmann, H., Bürg, I.M., and Conedera, M.
2010. Weather and human impacts on forest fires: 100 years of fire history in two climatic
regions of Switzerland. Forest Ecology and Management J. 261: 12. 2188-2199.
Doi:10.1016/j.foreco.2010.10.009.