Browsing by Author "Gil Costa, Verónica"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    ESSIM-EA applied to Wildfire Prediction using Heterogeneous Configuration for Evolutionary Parameters
    (2017-10-09) Méndez Garabetti, Miguel; Bianchini, Germán; Caymes Scutari, Paola; Tardivo, María; Gil Costa, Verónica
    Abstract. Wildfires devastate thousands forests acres every year around the world. Fire behavior prediction is a useful tool to cooperate in the coordination, mitigation and management of available resources to fight against this type of contingencies. However, the prediction of this phenomenon is usually a difficult task due to the uncertainty in the prediction process. Therefore, several methods of uncertainty reduction have been developed, such as the Evolutionary Statistical System with Island Models based on Evolutionary Algorithms (ESSIM-EA). ESSIMEA focuses its operation on an Evolutionary Parallel Algorithm based on islands, in which the same configuration of evolutionary parameters is used. In this work we present an extension of the ESSIM-EA that allows each island to select an independent configuration of evolutionary parameters. The heterogeneous configuration proposed, at the island level, with the original methodology in three cases of controlled fires has been contrasted. The results show that the proposed ESSIM-EA extension allows to improve the quality of prediction and to reduce processing times.
  • Thumbnail Image
    Item
    Hybrid-Parallel Uncertainty Reduction Method Applied to Forest Fire Spread Prediction
    (2017-04-01) Méndez Garabetti, Miguel; Bianchini, Germán; Tardivo, María; Caymes Scutari, Paola; Gil Costa, Verónica
    Fire behavior prediction can be a fundamental tool to reduce losses and damages in mergency situations. However, this process is often complex and affected by the existence of ncertainty. For this reason, from different areas of science, several methods and systems are developed and refined to reduce the effects of uncertainty In this paper we present the Hybrid Evolutionary-Statistical System with Island Model (HESS-IM). It is a hybrid uncertainty reduction method applied to forest fire spread prediction that combines the advantages of two evolutionary population metaheuristics: Evolutionary Algorithms and Differential Evolution. We evaluate the HESS-IM with three controlled fires scenarios, and we obtained favorable results compared to the previous methods in the literature