Abstract

In recent decades, in several parts of the world and under extreme weather conditions, we have witnessed the occurrence of numerous large-scale wildfires. This reality has also occurred in Portugal, burning thousands of hectares of forest, destroying infrastructures, and causing the regrettable loss of human lives. In view of this worsening panorama, we proceeded to the cartography of lLarge Forest Fires (LFF) in northwestern Portugal (larger than 100 hectares), in the period from 2001 to 2020, from the analysis of Landsat images and using Machine Learning tools and the Random Forest algorithm, in Google Earth Engine work environment. Based on the results obtained, an attempt is made to understand the LFF context in northwestern Portugal, as well as to analyse its spatial distribution and temporal evolution in the period under analysis. The conclusion is that about 158.741 ha burnt at least once and 40.9% of this area was affected by LFF a second time. The year of 2005 recorded the highest value of burnt area (73,025.1 ha). And the maximum recurrence observed, in the study area, was 7 occurrences, with a maximum recurrence of 6 times. The brush is the type of vegetation, in NUTS Ave, Alto Minho and Tâmega and Sousa, which presents more burnt area in LFF, while in Cávado, it is the forests that present the most extensive area covered by LFF. Thus, in 15 years for the study area, the most significant proportion of burnt vegetation corresponds to brush, being only in 5 years, forests were the class of the larger burnt area. In the current context of global changes and with large forest fires increasing in frequency, extent and intensity, its study and its temporal and spatial understanding are crucial, both at the regional and national scales.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.