Deteção de estruturas permanentes a partir de dados de séries temporais Sentinel 1 e 2

Mapping structures such as settlements, roads, individual houses and any other types of artificial structures is of great importance for the analysis of urban growth, masking, image alignment and, especially in the studied use case, the definition of Fuel Management Networks (FGC), which protect buildings from forest fires. Current cartography has a low generation frequency and their resolution may not be suitable for extracting small structures such as small settlements or roads, which may lack forest fire protection. In this paper, we use time series data, extracted from Sentinel-1 and 2 constellations, over Santar\'em, Ma\c{c}\~ao, to explore the detection of permanent structures at a resolution of 10 by 10 meters. For this purpose, a XGBoost classification model is trained with 133 attributes extracted from the time series from all the bands, including normalized radiometric indices. The results show that the use of time series data increases the accuracy of the extraction of permanent structures when compared using only static data, using multitemporal data also increases the number of detected roads. In general, the final result has a permanent structure mapping with a higher resolution than state of the art settlement maps, small structures and roads are also more accurately represented. Regarding the use case, by using our final map for the creation of FGC it is possible to simplify and accelerate the process of delimitation of the official FGC.