Remotely Sensed Data Fusion for Spatiotemporal Geostatistical Analysis of Forest Fire Hazard

Abstract

Forest fires are a natural phenomenon which might have severe implications on naturaland anthropogenic ecosystems. Future projections predict that, under a climate change environment,the fire season would be lengthier with higher levels of droughts, leading to higher fire severity.The main aim of this paper is to perform a spatiotemporal analysis and explore the variability of firehazard in a small Greek island, Skiathos (a prototype case of fragile environment) where the landuses mixture is very high. First, a comparative assessment of two robust modeling techniques wasexamined, namely, the Analytical Hierarchy Process (AHP) knowledge-based and the fuzzy logicAHP to estimate the fire hazard in a timeframe of 20 years (1996–2016). The former technique wasproven more representative after the comparative assessment with the real fire perimeters recorded onthe island (1984–2016). Next, we explored the spatiotemporal dynamics of fire hazard, highlightingthe risk changes in space and time through the individual and collective contribution of the mostsignificant factors (topography, vegetation features, anthropogenic influence). The fire hazard changeswere not dramatic, however, some changes have been observed in the southwestern and northernpart of the island. The geostatistical analysis revealed a significant clustering process of high-riskvalues in the southwestern and northern part of the study area, whereas some clusters of low-riskvalues have been located in the northern territory. The degree of spatial autocorrelation tends to begreater for 1996 rather than for 2016, indicating the potential higher transmission of fires at the mostsusceptible regions in the past. The knowledge of long-term fire hazard dynamics, based on multipletypes of remotely sensed data, may provide the fire and land managers with valuable fire preventionand land use planning tools.