Skip to main content

Advertisement

SpringerLink
Log in

Fire Risk Assessment Using Neural Network and Logistic Regression

  • Research Article
  • Published:
Journal of the Indian Society of Remote Sensing Aims and scope Submit manuscript

Abstract

Forest fire is one of the most important sources of land degradation that lead to deforestation and desertification processes. The presented work describes a methodology that employs logistic regression and artificial neural networks (ANN) to model forest fire risk and to recognize high potential area for fire occurrence. Different satellite and field data have been used in this work to model fire risk. These data include 12 static and dynamic parameters that are effective in fire occurrence and also 2001 to 2004 data was used to create model and data of year 2005 was used to evaluate created model. Two forest fire risk prediction models were created based on logistic regression and neural network in this research and both of them evaluated and compared. The result shows that neural network model is more accurate in fire point classification while logistic regression is sensitive to samples of fire points. To get high accuracy in logistic regression, it is necessary to be equilibrium the proportion of both fire and non-fire samples. Also different neural network structure was tested and the best architecture is a neural network with two hidden layer with 20, 28 neurons and logarithmic-sigmoid transfer function in both hidden layers. Accuracy of logistic regression and ANN in prediction of year 2005 fire was obtained 65.76 and 93.49, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  • Bachmann, A. & Allgower, B. (2000). The need for a consistent wildfire risk terminology. Paper Presented at the Proceeding from the Joint Fire Science Conference and Workshop: “crossing the millennium: integrating spatial technologies and ecological principles for a new age in fire management”, Boise, ID.

  • Ben-Akiva, M., & Lerman, S. R. (1985). Discrete choice analysis: Theory and application to travel demand. Cambridge: The MIT Press.

    Google Scholar 

  • Bishop, C. (1995). Neural networks for pattern recognition. New York: Oxford University Press.

    Google Scholar 

  • Catchpole, W. (2002). Fire properties and burn patterns in heterogeneous landscape. In R. A. Bradstock, J. E. Williams, & A. M. Gill (Eds.), Flammable Australian. The fire regimes ad biodiversity of a continent (pp. 46–75). Cambridge: Cambridge University Press.

    Google Scholar 

  • Chen, K., Blong, R., & Jacobson, C. (2001). Integrating multicriteria evaluation and GIS for risk decision-making in natural hazards. Environmental Modelling & Software, 16(2001), 387–397.

    Article  Google Scholar 

  • Chuvieco, E., & Salas, J. (1996). Mapping the spatial distribution of forest fire danger using GIS. International Journal of Geographic Information Science, 10(3), 333–345.

    Google Scholar 

  • Chuvieco, E., Salas, F. J., Carvacho, L., & Rodríguez-Silva, F. (1999). Integrated fire risk mapping. In E. Chuvieco (Ed.), Remote sensing of large wildfires in the European Mediterranean (pp. 61–84). Berlin: Springer.

    Chapter  Google Scholar 

  • Chuvieco, E., Allgöwer, B., & Salas, F. J. (2003a). Integration of physical and human factors in fire danger assessment. In E. Chuvieco (Ed.), Wildland fire danger estimation and mapping. The role of remote sensing data (pp. 197–218). Singapore: World Scientific Publishing.

    Chapter  Google Scholar 

  • Chuvieco, E., Aguado, I., Cocero, D., & Riaño, D. (2003b). Design of and empirical index to estimate fuel moisture content from NOAA-AVHRR images in forest fire danger studies. International Journal of Remote Sensing, 24, 1621–1637.

  • Deeming, J.E., Lancaster, J.W., Fosberg, M.A., Furman, R.W., & Schroeder, M.J. (1974). The national fire-danger rating system. USDA Forest Service, Rocky Mountain Forest and Range Experiment Station, Research Paper RM-84. Fort Collins, CO.

  • Egmont-Petersen, M., Ridder, D., & Handels, H. (2002). Image processing using neural networks—a review. Pattern Recognition, 35(10), 2279–2301.

    Article  Google Scholar 

  • FAO (2007). Fire management- global assessment 2006. FAO forestry paper No. 151. Rome.

  • Fiszelew, A., Britos, P., Ochoa, A., Merlino, H., Fernandez, E., & Garcıa-Martınez, R. (2007). Finding optimal neural network architecture using genetic algorithms. Advances in Computer Science and Engineering Research in Computing Science, 27, 15–24.

    Google Scholar 

  • Geman, S., Bienenstock, E., & Doursat, R. (1992). Neural networks and the bias/variance dilemma. Neural Computation, 4(1), 1–58.

    Article  Google Scholar 

  • Hagan, M. T., & Menhaj, M. (1994). Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), 989–993.

    Article  Google Scholar 

  • Hardly, C. (2005). Wildland fire hazard and risk: problem, definition, and context. Forest Ecology and Management, 211, 73–82.

    Article  Google Scholar 

  • Haykin, S. (1994). Neural networks. A comprehensive foundation. New York: Macmillan.

    Google Scholar 

  • Haykin, S. (1998). Neural networks: A comprehensive foundation (2nd ed.). Upper Saddle River: Prentice-Hall. 860 pp.

    Google Scholar 

  • Hosmer, D. W., & Lemeshow, S. (1989). Applied logistic regression. Wiley series in probability and mathematical statistics. New York: Wiley. 307 p.

    Google Scholar 

  • Huang, F., Xiang-nan, L., & Jin-guo, Y. (2000). Study on forest fire danger model with remote sensing based on GIS. Chinese Geographical Science, 10(1), 61–67.

    Article  Google Scholar 

  • Jafari Goldarag, Y., Mohammadzadeh, A., & Sarkargar Ardakani, A. (2011). Assessment and evaluation of some dynamic parameters effect on forest fire occurrence in Iran Southern forest using meteorological data and remote sensing. KNTU.

  • Jeffrey, T., et al. (2005). Validation of MODIS active fire detection products derived from two algorithms. Earth Interactions, 9, 1.

    Google Scholar 

  • Laneve, G. G., Castronuovo, M. M., & Cadau, E. G. (2006). Continuous monitoring of forest fires in the Mediterranean area using MSG. IEEE Transactions on Geoscience and Remote Sensing, 44(10), 2761–2768.

    Article  Google Scholar 

  • Leblon, B. (2001). Forest wildfire hazard monitoring using remote sensing, a review. Remote Sensing Reviews, 20(1), 1–57.

    Article  Google Scholar 

  • Levenberg, K. (1944). A method for the solution of certain non-linear problems in least squares. Quarterly of Applied Mathematics, 2(2), 164–168.

    Google Scholar 

  • Lozano, F. J., Suarez-Seoane, S., & de Luis, E. (2007). Assessment of several spectral indces derived from multi-temporal Landsat data for fire occurance probability modeling. Remote Sensing of Environment, 107, 533–544.

    Article  Google Scholar 

  • Marquardt, D. W. (1963). An algorithm for the least-squares estimation of nonlinear parameters. SIAM Journal of Applied Mathematics, 11(2), 431–441.

    Article  Google Scholar 

  • Martell, D. L., Otukol, S., & Stocks, B. J. (1987). A logistic model for predicting daily people-caused forest fire occurrence in Ontario. Canadian Journal of Forest Research, 17, 394–401.

    Article  Google Scholar 

  • Maselli, F., Rodolfi, A., Bottai, L., Romanelli, S., & Conese, C. (2000). Classification of Mediterranean vegetation by TM and ancillary data for evaluation of fire risk. International Journal of Remote Sensing, 21(17), 3303–3313.

    Article  Google Scholar 

  • Menard, S. W. (1995). Applied logistic regression analysis. Thousand Oaks: Sage Publications.

    Google Scholar 

  • Neeraj, S., & Hussin, Y.A. (1996). Spatial modeling for forest fire hazard prediction, management and control in Corbett national park, India. In J. Saramaki, B. Koch & H. G. Lund (Eds.), Remote sensing and computer technology for natural resources assessment (pp. 185–192). University of Joensuu.

  • Prechelt, L. (1998). Automatic early stopping using cross validation: quantifying the criteria. Neural Networks, 11(4), 761–767.

    Article  Google Scholar 

  • Prost, C., Zerger, A., & Dare, P. (2005). A multilayer feedforward neural network for automatic classification of eucalyptus forests in airborne video imagery. International Journal of Remote Sensing, 26(15), 3275–3293.

    Article  Google Scholar 

  • Pyne, S., Andrews, P. L., & Laven, R. D. (1996). Introduction to wildland fire. New York: Willey.

    Google Scholar 

  • Rathaur, S., Kushwaha, S.P.S., & Hussin, Y.A. (2006). Fire risk assessment for tiger prey-base in chilla range and vicinity, Rajaji National Park, India using remote sensing and GIS. Paper presented at ACRS Proceedings of the 27th Asian conference on remote sensing ACRS, 9–13 October, 2006 Ulanbaatar, Mongolia. Bangkok: Asian Association of remote sensing (AARS).

  • Roy, P.S. (2004). In M.V.K. Sivakumar, K. Harmesen & S.K. Saha (Eds.), Forest fire and degradation assessment using satellite remote sensing and geographic information system. satellite remote sensing and GIS application in agriculture meteorology (pp. 361–400). Geneva, Switzerland: World Meteorological Organization.

  • Salas, F. J., & Chuvieco, E. (1994). GIS application to forest fire risk mapping. Wildfire, 3, 7–13.

    Google Scholar 

  • Snayman, J, (2005) Practical mathematical optimization: An introduction to basic optimization theory and classical and new gradient-based algorithms. ISBN 978-0-387-24349-8.

  • Stroppiana, D., Pinnock, S., & Gregoire, J. M. (2000). The global fire product: daily fire occurrence from April 1992 to December 1993 derived from NOAA AVHRR data. International Journal of Remote Sensing, 21(6–7), 1279–1288.

    Article  Google Scholar 

  • VanWagner, C.E. (1974). Structure of the Canadian forest fireweather index. Canadian Department of Environment. Canadian Forestry Service, Publication 1333. Ottawa, ON.

  • Vasconcelos, M. J. P., Silva, S., Tomé, M., Alvim, M., & Pereira, J. M. C. (2001). Spatial prediction of fire ignition probabilities: comparing logistic regression and neural networks. Photogrammetric Engineering and Remote Sensing, 67, 73–83.

    Google Scholar 

  • Vega-García, C., Woodard, T., Adamowicz, W. L., & Lee, B. (1995). A logit model for predicting the daily occurence of human caused forest fires. International Journal of Wildland Fire, 5, 101–111.

    Article  Google Scholar 

  • Westerling, A.L. (2007). Climatology for wildfire management. In T.P. Holmes, J.P. Prestemon, & K.L. Abt (Eds.) Economics of forest disturbances—wildfires, storms, and invasive species. Springer-Verlag, 2008.

  • Westerling, A., Gershunov, D., Cayan, R., & Barnett, T. P. (2002). Long lead statistical forecasts of western U.S. wildfire area burned. International Journal of Wildland Fire, 11(3–4), 257–266.

    Article  Google Scholar 

  • Westerling, T., Brown, J., Gershunov, A., Cayan, D. R., & Dettinge, M. D. (2003a). Climate and wildfire in the western United States. Bulletin of the American Meteorological Society, 84, 595–604.

    Article  Google Scholar 

  • Westerling, A. Gershunov, & Cayan, D.R. (2003b) Statistical forecasts of the 2003 western wildfire season using canonical correlation analysis. Experimental Long-Lead Forecast Bulletin 12(1–2), Institute of Global Environment and Science, 71–75.

  • Westerling, A. H., Hidalgo, H. G., Cayan, D. R., & Swetnam, T. (2006). Warming and earlier spring increases western U.S. forest wildfire activity. Science, 313, 940–943.

  • Wright, R., Flynn, L., Garbeil, H., Harris, A., & Pilger, E. (2002). Automated volcanic eruption detection using MODIS. Remote Sensing of Environment, 82, 135–155.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Geomatic Engineering, Remote Sensing Department, K.N. Toosi University of Technology, Vali_Asr St. Vanaq Sq., Mirdamad Cr., Tehran, Iran

    Y. Jafari Goldarag & Ali Mohammadzadeh

  2. GIS and Remote Sensing Department, Imam Hussein University, Tehran, Iran

    A. S. Ardakani

Authors
  1. Y. Jafari Goldarag
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ali Mohammadzadeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. S. Ardakani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ali Mohammadzadeh.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jafari Goldarag, Y., Mohammadzadeh, A. & Ardakani, A.S. Fire Risk Assessment Using Neural Network and Logistic Regression. J Indian Soc Remote Sens 44, 885–894 (2016). https://doi.org/10.1007/s12524-016-0557-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12524-016-0557-6

Keywords

Search

Navigation