Uncovering Vegetation Changes in the Urban–Rural Interface through Semi-Automatic Methods

Forest fires are considered by Portuguese civil protection as one of the most serious natural disasters due to their frequency and extent. To address problem, Fire Defense System establishes implementation fuel management bands aid firefighting. The aim this study was develop a model capable identifying vegetation removal in urban–rural interface defined law for actions. uses normalised difference index (NDVI) Sentinel-2 images time series is based on Welch t-test find statistically significant differences between (i) value NDVI pixel; (ii) mean pixels same land cover type radius 500 m; (iii) difference. identifies change when points ‘pixel’ comparted ‘difference’ but not ‘mean’. We use moving window limited 60 days before after analysed date reduce phenological variations vegetation. applied five municipalities Portugal results promising identify places where carried out. This indicates which could be used assist verification annual law.