Dynamic Wildfire Fuel Mapping Using Sentinel – 2 and Prisma Hyperspectral Imagery

Italy has witnessed a significant increase in wildfires in recent decades. Forest fire fuel maps play a vital role in the prevention, management and risk assessment of wildfires, and this paper presents the procedure implemented to develop a dynamic wildfire fuel map using PRISMA hyperspectral data and Sentinel-2 multispectral data. Freely available multispectral datasets are widely used for land cover and land use mapping, but they have limited utility for fuel mapping due to their coarse spectral resolution. So, in this study, hyperspectral imagery (HSI) from PRISMA has been used for fuel types classification. The feed-forward neural network showed an overall accuracy of 79% by validation. To convert the classification map into a dynamic fuel map, the knowledge of the proportion of live/dead herbaceous loads available in that area is essential. The Relative Greenness approach, which places the Normalized Difference Vegetation Index (NDVI) in the time series of measurements, was implemented using Sentinel - 2 multispectral data. By fusing the fuel types classification, relative greenness map and iso-bioclimatic map, a dynamic fuel map for the west of Latium in Italy was developed with reference to Scott/Burgan fuel models.