Hybrid-parallel uncertainty reduction method applied to forest fire spread prediction

MIGUEL MENDEZ GARABETTI; GERMÁN BIANCHINI; MARÍA LAURA TARDIVO; PAOLA CAYMES SCUTARI; VERÓNICA GIL COSTA

Journal of Computer Science & Technology

RedUnci e ISTEC

Lugar: La Plata; Año: 2017 vol. 17 p. 12 - 19

1666-6046

Fire behavior prediction can be a fundamental tool to reduce losses anddamages in emergency situations. However, this process is often complex and affected by the existence of uncertainty. For this reason, fromdifferent areasof science, several methods and systems are developedand refined to reduce the effects of uncertainty. In this paperwe 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 twoevolutionary population metaheuristics: Evolutionary Algorithms andDifferential Evolution. We evaluate the HESS-IM with threecontrolled fires scenarios, and we obtained favorable results compared to the previous methods in the literature.