A Data Science Software Approach For Burned Forest Land Cover Classification and Co2 Emissions Calculation

Forest ecosystems are increasingly threatened by climate change and human activity. Portugal has been heavily affected. It suffered particularly severe and frequent fires in recent years. This research develops a method to assess the damage that a forest fire caused. The research consists of three main steps. Based on Remote Sensing the burned area after a fire is detected. A forest land cover map is generated by combining satellite images with the Portuguese forest inventory, indicating the dominant tree species with a resolution of 10 meters. Lastly, carbon emission/biomass loss is calculated on the basis of the forest composition. The research is carried out on the largest fire of 2024 in Portugal in the municipality of Reriz e Gafanhã. The satellite images from the Sentinel 2 mission are used.