Predicting the occurrence of wildfires with binary structured additive regression models

Abstract

Wildfires are one of the main environmental problems facing societies today, and in the case of Galicia (north-west Spain), they are the main cause of forest destruction. This paper used binary structured additive regression (STAR) for modelling the occurrence of wildfires in Galicia. Binary STAR models are a recent contribution to the classical logistic regression and binary generalized additive models. Their main advantage lies in their flexibility for modelling non-linear effects, while simultaneously incorporating spatial and temporal variables directly, thereby making it possible to reveal possible relationships among the variables considered. The results showed that the occurrence of wildfires depends on many covariates which display variable behaviour across space and time, and which largely determine the likelihood of ignition of a fire. The joint possibility of working on spatial scales with a resolution of 1 × 1 km cells and mapping predictions in a colour range makes STAR models a useful tool for plotting and predicting wildfire occurrence. Lastly, it will facilitate the development of fire behaviour models, which can be invaluable when it comes to drawing up fire-prevention and firefighting plans.

Complex Relationships of the Effects of Topographic Characteristics and Susceptible Tree Cover on Burn Severity

“…However, this assumption is highly questionable [10,50]. Linear correlation and regression are useful when quantifying the magnitude, direction and significance of the relationships between burn severity and environmental variables such as topographic variables and fuel types.…”

“…To avoid nonlinearity issues in dealing with the fire regime and environmental variables, a few approaches have been proposed such as artificial neural networks [51], stochastic processing [52] and spatial clustering [53]. Recently, flexible regression models, such as generalized additive models (GAMs; [54]), have been proposed to handle the nonlinear effects of continuous covariates on the response variable [50,55].…”

“…GAMs have been widely applied to investigate nonlinear relationships between dependent and non-explanatory variables in various fields of study such as plant and aquatic ecology (e.g., [58]) and water quality (e.g., [59]), as well as for nonlinear relationships among biotic and bon-biotic variables in environmental settings due to complex interactions between environmental factors. Many studies have identified nonlinear relationships among components of forest ecosystems (e.g., [3,50,[60][61][62][63][64][65]). In particular, Lee et al [3] reported that burn severity might be related to topographic characteristics such as elevation and slope.…”

“…Ríos-Pena et al [50] modeled the occurrence of wildfires in Galicia, Spain, using binary structured additive regression. Although they did not directly examine the nonlinear effects of susceptible fuels on burn severity, their results suggested a linear relationship between red pine trees and burn severity.…”

Evolution of Burned Area in Forest Fires under Climate Change Conditions in Southern Spain Using ANN

“…In the last decades, there have also been many studies of wildfires in Spain. For instance, Gallardo et al [43] used the logistic regression analysis to quantify changes in future fire occurrence due to future land use/land cover variations, Marcos et al [44] and Turco et al [29] explored the prediction of summer wildfires by developing a multiple linear regression model, Martin et al [45] employed the maximum entropy algorithm to analyze the intra-annual dimension of fire occurrence, Ríos Pena et al [46] explored the use of binary structured additive regression for prediction of wildfires, and Rodrígues et al [47] assessed the spatial-temporal changes in the contribution of wildfire drivers using geographically weighted logistic regression models. Concerning artificial intelligence techniques, Vasconcelos et al [48] obtained better results using an artificial neural network (ANN) than logistic regression.…”