Wildfire are increasingly frequent events on a planet undergoing climate change. With more favourable climate conditions for their occurrence, like prolonged periods of drought, the frequency and intensity of these catastrophes continue to increase. Protected areas are important territories for conserving ecosystems and biodiversity around the world and serve as a key management tool in national environmental policies. Many studies have been developed around the world to assess the conditions, frequency, and intensity of fires, and, on the other hand, protected areas are intensively studied to understand whether conservation actions are effective in keeping the ecosystem balanced. However, there are few studies that contemplate these two themes together. Consequently, this study offers a bibliometric analysis of the wildfires and its occurrence in protected areas, aiming to understand the spatial and temporal relation between them, characteristics of the research studies, and trending issues to be worked on. We used the Bibliometrix package in R language, which provides the option of different methods for analysing bibliometric data to understand the temporal evolution of the published documents about wildfires and protected areas. In total, 1116 publications were analysed, ranging from 1970 to 2022. The findings show that the terms “fires” (185 occurrences), “fire” (117), “wildfire” (101), and “forest fire” (92) are more frequently used and associated with studies on topics including biodiversity (304), conservation (221), environmental protection (188), deforestation (148), ecosystems (138), forestry (133), and climate change (126) as well as protected areas (399). The highest growth of research has been registered since 2002. The majority of the publications were published by authors from universities in the USA (77), South Africa (72), the United Kingdom (22), and Brazil (19). The USA leads all other countries with 7 of the top 10 international collaborations, followed by Brazil, Australia, and South Africa. However, only the United Kingdom continues to maintain an increased number of external (inter-country) collaborations, whereas the other nine continue to maintain an increased number of internal (intra-country). Considering the top 10 authors in terms of production, only 1 was active from 1999 to 2019, and the other 9 only have been active since 2009. The topics that stand out were subjected to a coupling analysis, which revealed that environmental protection is a motor theme, endangered species, Australia, and savannah are niche themes, and protected area, biodiversity, and fire management are basic themes.

Protected areas (PA) play an important role in minimizing the effects of soil erosion in watersheds. This study evaluated the performance of machine learning models, specifically support vector machine with linear kernel (SVMLinear), support vector machine with polynomial kernel (SVMPoly), and random forest (RF), on identifying indicators of soil erosion in 761 sub-watersheds and PA in northern Portugal, by using soil erosion by water in Europe, according to the revised universal soil loss equation (RUSLE2015), as target variable. The parameters analyzed were: soil erosion by water in Europe according to the revised universal soil loss equation (RUSLE2015), total burned area of the sub-watershed in the period of 1975-2020, fire recurrence, topographic wetness index (TWI), and the morphometric factors, namely area (A), perimeter (P), length (L), width (W), orientation (O), elongation ratio (Re), circularity ratio (Rc), compactness coefficient (Cc), form factor (Ff), shape factor (Sf), DEM, slope, and curvature. The median coefficient of determination (R²) for each model was RF (0.61), SVMpoly (0.68), and SVMLinear (0.54). Regarding the analyzed parameters, those that registered the greatest importance were A, P, L, W, curvature, and burned area, indicating that an analysis which considers morphometric factors, together with soil erosion data affected by water and soil moisture, is an important indicator in the analysis of soil erosion in watersheds.

Coastlines are suffering from the effects of erosive processes, the decrease in sediment supply, the rise in mean sea level, and the construction of coastal infrastructure and drainage works, which are further exacerbated by global climate change. The area of the Parque Natural do Litoral Norte (North Coast Natural Park) reveals worsening erosion rates and the transformations directly affect the natural resources that support tourism activities, particularly beach and nature tourism. As part of the CLICTOUR project, we have selected the coastline from Restinga de Ofir to Bonança Beach as a case study. The ESRI ArcGIS software and the Digital Shoreline Analysis System (DSAS) were used to quantify coastline migration and identify the impacts on beach morphology between 2010 and 2023. Based on this information, we calculated changes in carrying capacity and scenarios for visitor usage availability to ensure the protection of fauna and flora, as well as the safety of beachgoers. The results of the linear regression rate confirm the coastline has retreated during the period analyzed (2010–2023). The outcome of these dynamics is noticeable in the beach area, promoting its reduction in area and leisure quality. Considering climate change, this study shows the importance of developing resilience strategies for coastal territories that serve as traditional summer destinations.

Portuguese coastal zones are territories of great diversity but are subject to accelerated coastal dynamics. Recent and current coastline changes consist of erosive processes that cause the coastline to retreat and that become increasingly intense. These changes directly impact the natural resources that support sun and sea tourism, nautical tourism, health and wellness tourism and, especially, nature-based tourism. We selected the Litoral Norte Natural Park (PNLN) as a case study. As part of the CLICTOUR project, we sought to understand the coastline changes that occurred between 2010 and 2022, as well as the immediate and future impacts on the tourism sector for the territory, in general, and for the PNLN, in particular. This study focuses on the quantification of shoreline and dune morphology changes obtained with Unmanned Aerial Vehicles (UAV) and other remotely sensed data. The aerial images and the DEM obtained were analysed using ArcGIS. The calculation of shoreline changes was evaluated using statistical rates with the DSAS, and the morphological changes in sandy dunes were analysed with topographic data. The results were then compared to the existing tourism offer to evaluate the impacts of the sea level rise on bathing and nature tourism in this region.

Soil erosion increases after forest fires contributing to the mobilization, transport, and deposition of sediments and nutrients in watersheds. This scenario interferes with water quality. Faced with a climate change scenario, forest fires in the Mediterranean region tend to increase, consequently, soil erosion must increase together, aggravating water availability. Measures to minimize the effects of soil erosion in watersheds must be used to guarantee the water security of the population and protected areas play an important role in this context. This study analyzed 761 sub-watersheds in northern Portugal, to evaluate machine learning models in watersheds with recurrent fires. The analyzed area has a high recurrence of forest fires and where important districts of the country such as Porto and Braga with high population density are located, in addition to protected areas where springs of watercourses that integrate important watersheds such as Douro, Cávado, Ave, and Mondego. The parameters analyzed were: total burned area of ​​the sub-watershed in the period 1975-2020 (variable target), soil erosion by water in Europe - Revised Universal Soil Loss Equation (RUSLE2015), Topographic Wetness Index (TWI), and the morphometric parameters: Area (A), Perimeter (P), Length (L), Width (W), Orientation (O), Elongation ratio (Re), Circularity ratio (Rc), Compactness coefficient (Cc), Form factor (Ff), Shape factor ( Sf), Altitude, Slope, Curvature. These data was analyzed with the machine learning Generalized Linear Models (GLM), Support Vector Machine Linear (SVMLinear), Support Vector Machine Polynomial (SVMPoly) and Random Forest (RF). The analysis was developed in R language using the classification and regression training caret package. The average R2 for each model was RF (0.97), SVMpoly (0.96), SVMLinear (0.78) and GLM (0.78). In an analysis of boxplot plots of R2, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) the RF and SVMpoly models recorded lower dispersion of R2 and lower values ​​of MAE and RMSE. While the GLM and SVMlinear models showed greater data dispersion in the three accuracy measures of the models. Regarding the analyzed parameters, those that registered the greatest importance were A, Cc, P, Rc, W, RUSLE2015, and TWI, indicating that an analysis that considers morphometric parameters, together with soil erosion data by water and soil moisture is an important indicator in the analysis of soil erosion in watersheds. The study was developed within the scope of the CLICTOUR project (Project NORTE-01-0145-FEDER-000079), supporting fund European Regional Development Fund.Keywords: Soil erosion, sub-watersheds, machine learning, burned areas, water security.