Contrasting patterns and interpretations between a fire spread simulator and a machine learning model when mapping burn probabilities: A case study for Mediterranean areas. (May 2023)

• Record Type: Journal Article
• Authors: Costa-Saura, J.M.; Spano, D.; Sirca, C.; Bacciu, V.
• Is Part Of: Environmental modelling & software. Volume 163(2023)
• Publication Date: 2023-05
• Subjects: Wildfire simulators -- Burn probability -- Fire occurrence -- Fire likelihood -- Fire susceptibility -- Wildfire management; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2023.105685
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Two main approaches are commonly used to map fire-prone areas when designing firefighting and prevention campaigns: fire spread simulators and machine learning models. Despite they used mainly the same environmental variables, they differ in handling them. Thus, it is worth assessing differences in results and interpretations for supporting reliable decision-making process. Burn probabilities (BP) were calculated in Southern Italy using FlamMap and the Random Forest algorithm. Results showed contrasting spatial patterns, with Random Forest projecting more smoothed results than Flammap, which showed medium-high BP values only across some locations. In addition, BP from FlamMap and Random Forest differ across fuel types and environmental conditions. Results suggest that decisions based on fire simulators might be more tightly linked with actions preventing fire spread. In contrast, those based on machine learning might be more linked with fire occurrence elements not necessarily related to spreading, e.g., socioeconomic causes. Highlights: Burn probability differs between fire simulators and machine learning models. The relationships between environmental factors and BP change across approaches. Results interpretation depend on the approach used and it is mandatory.