Advertisement

Development of an Intelligent System for Predicting the Forest Fire Development Based on Convolutional Neural Networks

  • Tatiana S. StankevichEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1126)

Abstract

Forests are a natural renewable resource and can meet the needs of the society, provided that they are used for a multiple, rational, continuous and sustainable use. Forest fires are a natural component of forest ecosystems and cannot be completely eliminated. However, in recent decades, there has been a tendency to transform forest fires from a natural regulatory factor into a catastrophic phenomenon causing significant economic, environmental and social damage. It is critical to understand the relationships between the underlying environmental factors and spatial behaviour of a forest fire in order to develop effective and scientifically sound forest fire management plans. The key objective of this study is to enhance the efficiency of the formation of a real-time forest fire forecast under the unsteady and uncertain conditions. In the article, the author proposes to develop an intelligent system for predicting the forest fire development based on artificial intelligence and deep computer-aided learning. A key element of the system is forest fire propagation models that recognise data from successive images, predict the forest fire dynamics and generate an image with a fire propagation forecast. It is proposed to build forest fire propagation models by using a real-time forest fire forecasting method. In the article, the author presented a structural diagram of an intelligent system to forecast the dynamics of a forest fire and described the functional structure of the system by constructing its functional models in the form of IDEF0 diagrams.

Keywords

Artificial intelligence Deep machine learning Convolutional neural network (CNN) Wildfire Forest fire Real-time forecast Big data 

Notes

Acknowledgements

The reported study was funded by RFBR according to the research project № 18-37-00035 «mol_a».

References

  1. 1.
    Satir, O., Berberoglu, S., Donmez, C.: Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem. Geomat. Nat. Hazards Risk 7, 1645–1658 (2016)CrossRefGoogle Scholar
  2. 2.
    Dimopoulou, M., Giannikos, I.: Spatial optimization of resources deployment for forestfire management. Int. Trans. Oper. Res. 8, 523–534 (2001)CrossRefGoogle Scholar
  3. 3.
    Byram, G.M.: Combustion of forest fuels. In: Davis, K.P. (ed.) Forest Fire: Control and Use, pp. 61–89. McGraw-Hill, New York (1959)Google Scholar
  4. 4.
    UISIS. https://fedstat.ru. Accessed 29 July 2019
  5. 5.
    EFFIS. http://effis.jrc.ec.europa.eu. Accessed 29 July 2019
  6. 6.
    US Wildfires. https://www.ncdc.noaa.gov. Accessed 29 July 2019
  7. 7.
    Martínez, J., Vega-García, C., Chuvieco, E.: Human-caused wildfire risk rating for prevention planning in Spain. J. Environ. Manag. 90, 1241–1252 (2009)CrossRefGoogle Scholar
  8. 8.
    Martell, D.L.: A review of recent forest and wildland fire management decision support systems research. Curr. Forestry Rep. 1, 128–137 (2015)CrossRefGoogle Scholar
  9. 9.
    Sánchez, J.: Los incendios forestales y las prioridades de investigación en México. In: Congreso Forestal Mexicano, México, pp. 719–723 (1989)Google Scholar
  10. 10.
    Silva, F.R., Guijarro, M., Madrigal, J., Jimenez, E., Molina, J.R., Hernando, C., Velez, R., Vega, J.A.: Assessment of crown fire initiation and spread models in Mediterranean conifer forests by using data from field and laboratory experiments. Forest Syst. 26(2), 14 (2017).  https://doi.org/10.5424/fs/2017262-10652CrossRefGoogle Scholar
  11. 11.
    Sullivan, A.L.: Wildland surface fire spread modelling, 1990–2007. 1: physical and quasi-physical models. Int. J. Wildland Fire 18, 349–368 (2009)CrossRefGoogle Scholar
  12. 12.
    Sullivan, A.L.: Wildland surface fire spread modelling, 1990–2007. 2: empirical and quasi-empirical models. Int. J. Wildland Fire 18, 369–386 (2009)CrossRefGoogle Scholar
  13. 13.
    Sullivan, A.L.: Wildland surface fire spread modelling, 1990–2007. 3: simulation and mathematical analogue models. Int. J. Wildland Fire 18, 387–403 (2009)CrossRefGoogle Scholar
  14. 14.
    Perminov, V., Goudov, A.: Mathematical modeling of forest fires initiation, spread and impact on environment. Int. J. Geomate 13(35), 93–99 (2017). http://www.geomatejournal.com/sites/default/files/articles/93-99-6704-Valeriy-July-2017-35-a1.pdf
  15. 15.
    Shi, Y.: A probability model for occurrences of large forest fires. Int. J. Eng. Manuf. (IJEM) 1, 1–7 (2012).  https://doi.org/10.5815/ijem.2012.01.01CrossRefGoogle Scholar
  16. 16.
    Adab, H., Kanniah, K.D., Solaimani, K.: Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques. Nat. Hazards 65, 1723–1743 (2013)CrossRefGoogle Scholar
  17. 17.
    Safi, Y., Bouroumi, A.: Prediction of forest fires using artificial neural networks. Appl. Math. Sci. 7, 271–286 (2013)Google Scholar
  18. 18.
    Agarwal, P.K., Patil, P.K., Mehal, R.: A methodology for ranking road safety hazardous locations using analytical hierarchy process. Proc. - Soc. Behav. Sci. 104, 1030–1037 (2013)CrossRefGoogle Scholar
  19. 19.
    Angayarkkani, K., Radhakrishnan, N.: An effective technique to detect forest fire region through ANFIS with spatial data. In: 3rd International Conference on Electronics Computer Technology (ICECT), Kanyakumari, India, p. 2430 (2011).  https://doi.org/10.1109/ICECTECH.2011.5941794
  20. 20.
  21. 21.
    FlamMap. https://www.firelab.org/project/flammap. Accessed 29 July 2019
  22. 22.
    FARSITE. https://www.firelab.org/project/farsite. Accessed 29 July 2019
  23. 23.
    Stankevich, T.S.: Operational prediction of the forest fire dynamics. In: VI International Baltic Maritime Forum 2018: XVI International Scientific Conference “Innovation in Science, Education and Entrepreneurship-2018”, pp. 1079–1087. Izdatelstvo BGARF, Kaliningrad, Russia (2018). (in Russian)Google Scholar
  24. 24.
    Hussain, M., Dey, E.K.: Remote sensing image scene classification. J. Manuf. Sci. Eng. 4, 13–20 (2018)Google Scholar
  25. 25.
    SO/IEC 25010:2011: Systems and software engineering. Systems and Software Quality Requirements and Evaluation (SQuaRE). System and Software Quality Models. Standartinform, Mocsow (2009)Google Scholar
  26. 26.
  27. 27.
    Land Cover Map ESA/CCI. http://maps.elie.ucl.ac.be/CCI/viewer/. Accessed 29 July 2019
  28. 28.
    Ventusky InMeteo. https://www.ventusky.com. Accessed 29 July 2019
  29. 29.
  30. 30.
    Jay Kuo, C.-C.: Understanding convolutional neural networks with a mathematical model. J. Vis. Commun. Image Represent. 41, 406–413 (2016)CrossRefGoogle Scholar
  31. 31.
    Nemkov, R.M., et al.: Using of a convolutional neural network with changing receptive fields in the tasks of image recognition. In: Proceedings of the First International Scientific Conference, IITI 2016, pp. 15–25. Springer, Switzerland (2016)Google Scholar
  32. 32.
    Unsupervised methods. Diving deep into autoencoders. https://www.cl.cam.ac.uk/~pv273/slides/UCLSlides.pdf. Accessed 29 July 2019

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Kaliningrad State Technical UniversityKaliningradRussian Federation

Personalised recommendations