Abstract
Forest fires prediction represents a great computational and mathematical challenge. The complexity lies both in the definition of mathematical models for describing the physical phenomenon and in the impossibility of measuring in real time all the parameters that determine the fire behaviour. ESSIM (Evolutionary Statistical System with Island Model) is an uncertainty reduction method that uses Statistic, High Performance Computing and Evolutionary Strategies in order to guide the search towards better solutions. ESSIM has been implemented with two different search strategies: the method ESSIM-EA uses Evolutionary Algorithms as optimization engine, whilst ESSIM-DE uses the Differential Evolution algorithm. ESSIM-EA has shown to obtain good quality of predictions, while ESSIM-DE obtains better response times. This article presents an alternative to improve the quality of solutions reached by ESSIM-DE, based on the analysis of the relationship between the evolutionary strategy convergence speed and the population distribution at the beginning of each prediction step.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bianchini, G., Denham, M., Cortés, A., Margalef, T., Luque, E.: Wildland fire growth prediction method based on multiple overlapping solution. J. Comput. Sci. 1(4), 229–237 (2010)
Méndez Garabetti, M., Bianchini, G., Caymes Scutari, P., Tardivo, M.L.: Sistema Estadístico Evolutivo con Modelo de Islas: Calibración de parámetros evolutivos. In: International Symposium on Innovation and Technology, Lima, Perú, pp. 77–81 (2015)
Méndez Garabetti, M., Bianchini, G., Caymes Scutari, P., Tardivo, M.L.: ESS-IM applied to forest fire spread prediction: parameters tuning for a heterogeneous configuration. In: International Symposium SCCC 2016, Valparaiso, Chile, pp. 514–525 (2016)
Tardivo, M.L., Caymes-Scutari, P., Bianchini, G., Méndez-Garabetti, M.: Ajuste de Parámetros Evolutivos para el Método Paralelo de Reducción de Incertidumbre ESSIM-DE. XXII Congreso Argentino de Ciencias de la Computación, San Luis, Argentina, pp. 4–13 (2016)
Tardivo, M.L., Caymes-Scutari, P., Bianchini, G., Méndez-Garabetti, M.: Reducción de incertidumbre con Evolución Diferencial en la predicción de incendios forestales: sintonización y análisis de parámetros. Mec. Comput. 34, 2903–2917 (2016)
Méndez Garabetti, M., Bianchini, G., Tardivo, M.L., Caymes Scutari, P.: Evolutionary-statistical system with Island model for forest fire spread prediction. In: VI Latin American Symposium on High Performance Computing, Mendoza, Argentina, pp. 61–64 (2013)
Tardivo, M.L., Caymes-Scutari, P., Bianchini, G., Méndez-Garabetti, M., Cortés, A.: Three evolutionary statistical parallel methods for uncertainty reduction in wildland fire prediction. In: International Conference on High Performance Computing & Simulation, Innsbruck, Austria, pp. 721–728 (2016)
Talbi, E.: Metaheuristics: From Design to Implementation. Wiley, New Jersey (2009)
Viegas D.X.: Project spread - forest fire spread prevention and mitigation. http://www.algosystems.gr/spread/
Price, K., Storn, R., Lampinen, J.: Differential Evolution - A Practical Approach to Global Optimization. Springer-Verlag New York, Inc., USA (2005). https://doi.org/10.1007/3-540-31306-0
Acknowledgements
This work has been supported by UTN under the projects EIUTIME0003939TC and EIUTNME0003952, and by MEC-Spain under the project TIN2014-53234-C2-1-R. The first author would like to thank CONICET for the PhD Grant provided.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Tardivo, M.L., Caymes-Scutari, P., Méndez-Garabetti, M., Bianchini, G. (2018). Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction. In: De Giusti, A. (eds) Computer Science – CACIC 2017. CACIC 2017. Communications in Computer and Information Science, vol 790. Springer, Cham. https://doi.org/10.1007/978-3-319-75214-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-75214-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75213-6
Online ISBN: 978-3-319-75214-3
eBook Packages: Computer ScienceComputer Science (R0)