A comparative study of evolutionary statistical methods for uncertainty reduction in forest fires propagation prediction

TARDIVO, MARÍA LAURA; CAYMES SCUTARI, PAOLA; BIANCHINI, GERMÁN; MENDEZ GARABETTI, MIGUEL; CENCERRADO, ANDRÉS; CORTÉS, ANA

Procedia Computer Science

Elsevier

Año: 2017 vol. 108 p. 2018 - 2027

1877-0509

Predicting the propagation of forest fires is a crucial point to mitigatetheir effects. Therefore, several computational tools or simulators havebeen developed to predict the fire propagation. Such tools consider thescenario (topography, vegetation types, fire front situation), and theparticular conditions where the fire is evolving (vegetation conditions,meteorological conditions) to predict the fire propagation. However,these parameters are usually difficult to measure or estimate precisely,and there is a high degree of uncertainty in many of them. Thisuncertainty provokes a certain lack of accuracy in the predictions withthe consequent risks. So, it is necessary to apply methods to reduce theuncertainty in the input parameters. This work presents a comparison ofESSIM-EA and ESSIM-DE: two methods to reduce the uncertainty in the inputparameters. These methods combine Evolutionary Algorithms, Parallelismand Statistical Analysis to improve the propagation prediction.