Application of artificial neural network for forest fire risk mapping based on physiographic, human and climate factors in Sarvabad, Kurdistan province

Document Type : Research Paper

Authors

1 M. Sc., Faculty of Natural Resources, University of Kurdistan, Sanandaj, Iran.

2 Assistant Professor, Faculty of Natural Resources, University of Kurdistan, Sanandaj, Iran.

Abstract

The protective role of the Zagros forests in preventing soil and water erosion is very important. Therefore forest fires account as major environmental hazards for Zagros forests. The aim of this research was to study the influence of variables on fire occurrence and producing fire susceptibility map. Factors affecting fire incidences include altitude, slope, aspect, distance to residential areas, distance to roads and farmlands, temperature and rain. These factors were examined to determine the effect of each variable in occurrence of fire. Sampling procedures was performed in forest areas with previous fire records and in non- affected forest areas and MLP method was used to determine the importance of each factor in the occurrence of fires. Sensitivity maps of different areas to fire were produced using artificial neural network method. Results showed that the slope (100%) and distance to roads (95%) variables are most important factors influencing fire occurrence while aspect with 55% effect has the least correlation with fire occurrence. The model was further validated with Kappa coefficients. Results indicate that the sensitivity map is produced with 90% accuracy, and that 98% of the grid cells are correctly classified.

Keywords

References

- اسکندری، س.، اولادی قادیکلایی، ج.، جلیلوند، ح. و سراجیان، م.، 1392. مدل­سازی و پیش­بینی خطرآتش­سوزی در جنگل­های بخش سه نکا- ظالمرود با استفاده از سامانه اطلاعات جغرافیایی. فصلنامه علمی– پژوهشی تحقیقات جنگل و صنوبر ایران، 21(2): 217- 203.
- بلندهمت، ا.، 1386. اثرات آتش­سوزی روی برخی خصوصیات فیزیکی و شیمیائی خاک جنگل‌های منطقه مریوان. پایان‎نامه کارشناسی ارشد، دانشکده منابع طبیعی و علوم دریایی دانشگاه تربیت مدرس، ص 85.
-بی‎نام، 1386. آمار آتش‎سوزی 4 سال. سازمان جنگل‌ها و مراتع کل کشور ، 36 صفحه.
-رحیمی، ا. و اسماعیلی، ع.، 1389. بررسی پتانسیل آتش‎سوزی جنگل‎ها و مراتع با استفاده از تصاویر ماهواره‎ای سنجندهMODIS  و تکنیک‎های سنجش از دور منطقه مورد مطالعه جنگل‎های شهرستان مریوان. همایش ژئوماتیک، 12 صفحه.
-سرکارگر اردکانی، ع.، ولدان زوج، م. و منصوریان، ع.، 1388. تحلیل فضایی نیروی آتش‎سوزی مناطق مختلف کشور با استفاده از RS, GIS. محیط‎شناسی، 52: 34-25.
-گراوند، س.، یارعلی، ن. و کاجی، ح.، 1392. الگوی مکانی و نقشه خطر وقوع آتش­سوزی در اراضی طبیعی استان لرستان. فصلنامه علمی- پژوهشی تحقیقات جنگل و صنوبر ایران، 21 (2): 242- 231.
-محمدی، ف.، 1388. تهیه نقشه خطر آتش‎سوزی جنگل با استفاده از تصاویر ماهواره‎ای و GIS در بخشی از جنگل‎های پاوه. پایان‎نامه کارشناسی‎ارشد، گروه جنگلداری. دانشکده منابع طبیعی، دانشگاه کردستان، 64 صفحه.
 
- Andersson, F. O., Aberg, M. and Jacobsson, S. P., 2000. Algorithmic approaches for studies of variable influence, contribution and selection in neural networks. Chemometrics and Intelligent Laboratory Systems, 51(1): 61–72.
- Bajocco, S., Rosalti, L. and Ricotta, C., 2009. Knowing fire incidence through fuel phenology. A remotely sensed approach. Ecological Modelling, 59-66.
- Banazountas, M., Kallidromitou, D., Kassamenos, P. and Passes, N., 2006. A decision support system for managing forest fire casualties. Journal of Environmental Management, 84(4):412-418.
- Dayhoff, J. E., 1990. Neural Network Architectures. VNR. USA.
- Dong, X., Li-min, D., Gue- fan, Sh., Lei, T. and Hui, W., 2005. Forest fire risk zone mapping from satellite images and GIS for Baihe forestry Bureau, Jilin, China. Journal of Forestry Research. (16)3: 169- 174.
- Erten, E., Kurgun,V. and Musaoglue, N., 2004. Forest fire risk zone mapping from satellite imagery and GIS a case study. Proceedings of 20th Congress of ISPRS, Istanbul, Turkey, 29-33.
- Etter, A., McAlpine, C.,Wilson, K., Phinn, S. and Possingham, H. 2006. Regional patterns of agricultural land use and deforestation in Colombia. Agric. Ecosystems & Environment, 114: 369-386.
- Garcia Strino, J., Alhaddad, B. and RocaGladera, J. 2007. Remote sensing to detect fire risk locations. GéoCongrés, 2-5 octobre.
- Hawes, P., Crook, N., 1999. Using input parameter influence to support the decisions of feedforward neural networks. Neurocomputing, 24: 191-206.
- Hernandez-Leal, P. A., Arbelo, M. and Gonzalez-Clavo, A., 2006. Fire risk assessment using satellite data. Advances in space research, 37: 741- 746.
- Jaiswal, R. K., Mukerjee, S., Raju, D. K. and Saxana, R., 2002. Forest fire risk zone mapping from satellite imagery and GIS. International Journal of Applied Earth observation and Geoinformation, 4: 1-10.
- Pointius, R. G., 2000. Quantification Error versus location Error in comparison of categorical Maps. Photogrammetric Engineering & Remote sensing, 66(8): 1011-1016.
- Sakr, G. E., Elhajj, I. H. and Mitri, G., 2011. Efficient forest fire occurrence prediction for developing countries using two weather parameters. Engineering applications of artificial intelligence. 24: 888 -894.
- Setiawan, I; Mahmud, A; Masnsor, S; Shariff, A; Nuruddin, A; 2004. GIS- grid- based and multi- criteria analysis for identifying and mapping peat swamp forest fire hazard in Pahang, malysia. Disaster Prevention And Management. 13: 379- 386.

-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. Journal of the Indian Society of Remote Sensing. 37: 37-50.

- Vasilokos, CH; Kalabokidis, K; Hatzopoulos, J; Kallos, G; Matsinos, Y;2007. Integrating new methods and tools in fire danger rating. International Journal Of Wildland Fire. 16: 306 – 316.

-Yang, L., Dawson, C. W., Brown, M. R. and Gell, M., 2006. Neural network and GA approaches for dwelling fire occurrence prediction. Knowledge-Based Systems, 19(4): 213- 219.
-Yuan,H., 2002. Development and evaluation of advanced classification systems using remotely sensed data for accurate land use/ land-cover mapping. Ph. D, Thesis, Department of forestry, North Carolina state university.
-Zeng, T., Hudson, J., Kay, S. and Laginestra, E., 2003. A fuzzy GIS approach to fire risk assessment: a case study of Sydney Olympic park, Australia. Spatial Sciences Conferences, 1-20 

Files

History

  • Receive Date: 30 April 2013
  • Revise Date: 13 September 2014
  • Accept Date: 06 November 2013

Share

How to cite

Statistics