Fire severity assessment of an alpine forest fire with sentinel-2 imagery
University of New Brunswick
Fire is a common phenomenon in many forests and is considered as an important ecological tool. Fire severity mapping presents an effective way to assess post-fire management intervention and is very useful in ecological and climate change research. The objective of this study was to assess the severity of a forest fire event which occurred from 24th to 27th October 2019 at Taibon Agordino using Sentinel 2A satellite and creating a severity map suitable as a decision-making tool for post-fire management intervention. The Sentinel 2A satellite data was classified into the following five classes: Unburnt, Low Severity, Intermediate Severity, High Severity and Shadow with the nonparametric Random Forest (RF) classifier and the resulting classification was validated using validation sites. The RF classifier was applied first to the 10 original bands of Sentinel-2. In a second step, additional variables were added to the classification, namely the digital elevation model (DEM), the slope, and five vegetation indices (i.e., Differenced Normalized Burn Ratio (dNBR), Relative Differenced Normalized Burn Ratio (RdNBR), Differenced Bare Soil Index (dBSI), Global Environmental Monitoring Index (GEMI) and Burn Area Index (BAI)) The inclusion of vegetation indices and DEM-related variables increased the classification accuracy from 99.26% to 99.61% and the overall accuracy from 70.51% to 83.33%. In the RF with 10 original bands, the variable of importance plot ranked the Red Edge 3, Red and SWIR 1 bands as the top three most important, while in the RF classification with 17 variables RdNBR, DEM and dNBR were ranked as the top 3 most important variables.