Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest

• Published in: Forest ecology and management 2012-07, Vol.275, p.117-129
• Main Authors: Oliveira, Sandra, Oehler, Friderike, San-Miguel-Ayanz, Jesús, Camia, Andrea, Pereira, José M.C.
• Format: Article
• Language: English
• Subjects: Animal and plant ecology; Animal, plant and microbial ecology; Biological and medical sciences; Density; Fire occurrence; Fires; Forestry; Forests; Fundamental and applied biological sciences. Psychology; Mathematical models; Mediterranean Europe; Multiple Linear Regression; Random Forest; Regression; Regression analysis; Spreads; Synecology; Terrestrial ecosystems
• ISSN: 0378-1127; 1872-7042
• DOI: 10.1016/j.foreco.2012.03.003

► We model spatial patterns of fire occurrence in Mediterranean Europe with two methods. ► Random Forest method showed a better performance than Multiple Linear Regression. ► NW Iberian Peninsula and South Italy have higher likelihood of fire occurrence. ► Precipitation is the most important variable with both methods. ► Local roads density, livestock density and unemployment rate are also significant. Fire occurrence, which results from the presence of an ignition source and the conditions for a fire to spread, is an essential component of fire risk assessment. In this paper, we present and compare the results of the application of two different methods to identify the main structural factors that explain the likelihood of fire occurrence at European scale. Data on the number of fires for the countries of the European Mediterranean region during the main fire season (June–September) were obtained from the European Fire Database of the European Forest Fire Information System. Fire density (number of fires/km2) was estimated based on interpolation techniques and was used as the dependent variable in the model. As predictors, different physical, socio-economic and demographic variables were selected based on their potential influence in fire occurrence and on their availability at the European level. Two different methods were applied for the analysis: traditional Multiple Linear Regression and Random Forest, the latter being a non-parametric alternative based on an ensemble of classification and regression trees. The predictive ability of the two models, the variables selected by each method and their level of importance were compared and the potential implications to forest management and fire prevention were discussed. The Random Forest model showed a higher predictive ability than Multiple Linear Regression. Furthermore, the analysis of the residuals also indicated a better performance of the Random Forest model, showing that this method has potentiality to be applied in the assessment of fire-related phenomena at a broad scale. Some of the variables selected are common to both models; precipitation and soil moisture seem to influence fire occurrence to a large extent. Unemployment rate, livestock density and density of local roads were also found significant by both methods. Maps of the likelihood of fire occurrence were obtained from each method at 10km resolution, based on the selected variables. Both models show that the spatial distribution of fire