Hybrid-Parallel Uncertainty Reduction Method Applied to Forest Fire Spread Prediction

• Main Authors: Miguel Méndez Garabetti, Germán BIanchini, María Laura Tardivo, Paola Caymes Scutari, Graciela Verónica Gil Costa
• Format: Article
• Language: English
• Published: Postgraduate Office, School of Computer Science, Universidad Nacional de La Plata 2017-04-01
• Series: Journal of Computer Science and Technology
• Subjects: hybrid metaheuristics; differential evolution; evolutionary algorithms; fire prediction; uncertainty reduction
• Online Access: https://journal.info.unlp.edu.ar/JCST/article/view/455

Fire behavior prediction can be a fundamental tool to reduce losses and damages in emergency situations. However, this process is often complex and affected by the existence of uncertainty. 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.