Development of a convolutional neural network to accurately detect land use and land cover.

The detection and modeling of Land Use and Land Cover (LULC) play pivotal roles in natural resource management, environmental modeling and assessment, and ecological connectivity management. However, addressing LULCC detection and modeling constitutes a complex data-driven process. In the present study, a Convolutional Neural Network (CNN) is employed due to its great potential in image classification. The development of these tools applies the deep learning method. A methodology has been developed that classifies the set of land uses in a natural area of special protection. This study area covers the Sierra del Cando (Galicia, northwest Spain), considered by the European Union as a Site of Community Interest and integrated in the Natura 2000 Network. The results of the CNN model developed show an accuracy of 91 % on training dataset and 88 % on test dataset. In addition, the model was tested on images of the study area, both from Sentinel-2 and PNOA. Despite some confusion especially in the residential class due to the characteristics in this area, CNNs prove to be a powerful classification tool.•Classifications based on a CNN model•LULC are classified into 10 different classes•Training and test accuracy are 91 % and 88 %, respectively.

Sediment source fingerprints of natural processes and anthropogenic pressures: A contribution to manage the Paraopeba River basin impacted by the B1 tailings dam collapse.

Understanding the origins of sediment transport in river systems is crucial for effective watershed management, especially after catastrophic events. This information is essential for the development of integrated strategies that guarantee water security in river basins. The present study aimed to investigate the rupture of the B1 tailings dam of the Córrego do Feijão mine, which drastically affected the Brumadinho region (Minas Gerais, Brazil). To address this issue, a confluence-based sediment fingerprinting approach was developed through the SedSAT model. Uncertainty was assessed through Monte Carlo simulations and Mean Absolute Error (MAE). Estimates of the overall average contributions of each tributary were quantified for each station and annually during the period 2019-2021. It was observed that the sampling point PT-09, closest to the dam breach, contributed to almost 80% of the Paraopeba River in 2019. Despite the dredging efforts, this percentage increased to 90% in 2020 due to the need to restore the highly degraded area. Additionally, the main tributaries contributing to sediment increase in the river are Manso River "TT-03" (almost 36%), associated with an area with a high percentage of urban land use, and Cedro stream "TT-07" (almost 71%), whose geology promotes erosion, leading to higher sediment concentration. Uncertainties arise from the limited number of available tracers, variations caused by dredging activities, and reduced data in 2020 due to the pandemic. Parameters such as land use, riparian vegetation degradation, downstream basin geology, and increased precipitation are key factors for successfully assessing tributary contributions to the Paraopeba River. The obtained results are promising for a preliminary analysis, allowing the quantification of key areas due to higher erosion and studying how this disaster affected the watershed. This information is crucial for improving decision-making, environmental governance, and the development of mitigating measures to ensure water security. This study is pioneering in evaluating this methodology in watersheds affected by environmental disasters, where restoration efforts are ongoing.

Geospatial mapping of carbon estimates for forested areas using the InVEST model and Sentinel-2: A case study in Galicia (NW Spain).

CO2 emissions have increased exponentially in recent years, so measuring and quantifying carbon sequestration is a step towards sustainable forest management and combating climate change. The overall goal of this study is to develop an accurate model for estimating carbon storage and sequestration for forest areas of the Atlantic Biogeographic Region. Specifically, the modelling and field sampling are carried out in the municipality of Baiona (Galicia, NW Spain), which was selected as a representative biome of this region. The methodology consists of carrying out two object-based image analysis (OBIA) classifications in spring and autumn to observe possible stocks of seasonal differences. Two carbon storage and sequestration models are built up (model 1 and model 2): model 1 for forest areas only and model 2 including all other land cover in the study area. Sentinel-2 geospatial data for 2021, Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) tools and geographic information systems (GIS) are used. A Kappa index of 0.92 is obtained for both classifications, thus ruling out any notable seasonal differences in the images used. The results from both models indicate that it is land covers associated with forest uses which store the most carbon in the study area, accounting for >50 % more than the other land covers. It is concluded that the methodology and data used are very useful for quantifying ecosystem services, which will help the governance of the region by implementing measures to mitigate some of the effects of climate change and help to create silvicultural models for the sustainable management of the Atlantic Biogeographic Region.

Assessment of high spatial resolution satellite imagery for monitoring riparian vegetation: riverine management in the smallholding.

Riverine habitats are essential ecotones that bridge aquatic and terrestrial ecosystems, providing multiple ecosystem services. This study analyses the potential use of high-resolution satellite imagery, provided by the WorldView-2 satellite, in order to assess its viability for monitoring riparian ecosystems. It is performed by calculating the riparian strip quality index (RSQI) and calibrating it with the riparian quality index (QBR). The methodology was implemented in the Umia River, which is characterised by elevated anthropogenic pressures (located in the northwest of Spain). The results obtained by the method have a 92% of veracity and a kappa coefficient of 0.88. The average quality value obtained for the RSQI index was 71.57, while the average value for the QBR was 55.88. This difference could be attributed to the fact that the former does not differ between autochthonous and non-autochthonous vegetation. The areas with more accurate mapping corresponded to stretches of vegetation with optimal cover (80-50%), with good connectivity with the adjacent forest ecosystem and few or no presence of invasive plants. The worst-scoring sites had the next characteristics: low connectivity (< 10%), low forest cover (< 10%) and a higher presence of invasive plants. The degradation of vegetation could be explained by the presence of agriculture and deficient land use rationing caused by the type of ownership of the study area. The application of this index through satellite images will facilitate the environmental governance of multiple ecosystems and in special riparian ecosystems, obtaining a quick and objective methodology, easily replicable in other basins.

Modelling of threats that affect Cyano-HABs in an eutrophicated reservoir: First phase towards water security and environmental governance in watersheds.

Cyano-HABs are proliferating around the world due to anthropogenic nutrient enrichment of freshwater bodies. This study seeks to obtain a holistic vision over the various threats that affect the Cyano-HABs of Umia basin and especially of A Baxe reservoir (Galicia, NW Spain), through the method of Partial least squares path modelling (PLS-PM). The A Baxe reservoirs is a fundamental source of drinking water supply to surrounding dwellings. This study identifies and quantify the variables that increase contaminant concentration and decrease ecological integrity, as well as how this scenario evolved over various hydrologic years. In this regard, the PLS-PM equations will be robust and powerful tools to predict changes in eutrophication and ecological integrity, as response to measures implemented in the basin that can improve water quality. The dependent latent variables are "Eutrophication" (chlorophyl-a, Microcystis sp.) and "Ecological Integrity" (METI Bioindicator). The independent latent variables are "SWP", which represents surface water parameters (phosphorus, nitrogen and pH) and "Climatic Conditions" (temperature, precipitation). The PLS-PM results revealed that 51.0% of "Eutrophication" is predicted by the independent variables. The connections between latent variables are quantified through path coefficients (ß). The "SWP" contributes by increasing "Eutrophication" (ß = 0.235), the same occurring with the "Climatic Conditions" (ß = -0.672). The variables "Eutrophication" (ß = -0.217) and "SWP" (ß = -0.483) lower the "Ecological Integrity". On the other hand, different trophic scenarios, adapted to the temperature increase predicted for the study area, were tested, and it was found that ecological integrity would improve by 46% if the oligotrophic state were reached. Therefore, it is recommended to prevent pollution by means of water control and governance plans, as well as corrective and preventive measures, which guarantee the water security of the river basins. Despite the complex mathematics behind the PLS-PM models, their user-friendly development and application through interactive graphical interfaces make them easily transposable to other eutrophic reservoirs, widening the readership of these studies focused on multiple-geosphere assessment of environmental impacts.

Water security and watershed management assessed through the modelling of hydrology and ecological integrity: A study in the Galicia-Costa (NW Spain).

Water management is a crucial tool for addressing the increasing uncertainties caused by climate change, biodiversity loss and the conditions of socioeconomic limits. The multiple factors affecting water resources need to be successfully managed to achieve optimal governance and thus move towards water security. This study seeks to obtain a holistic vision of the various threats that affect the ecological integrity of the basins that form the hydrological district of Galicia-Costa, through the method of partial least squares path modelling (PLS-PM). The data is analysed overall for the hydrological years from 2009 to 2015. The independent latent variables are "Anthropogenic" (comprising the percentage of water bodies with edges alongside artificial surfaces, the percentage connected to artificial land use patches, the edge density of artificial surfaces and population density) and "Nature" (edge density of forestry land uses, edge length of land water bodies alongside forested areas and the percentage of land occupied by the largest patch of forest). The dependent latent variables are "SWP", which represents surface water parameters (biological oxygen demand, chlorides, conductivity and dissolved iron) and "Ecological Integrity" (METI Bioindicator). The connections between latent variables are uantified through path coefficients (ß). From an overall perspective, the PLS-PM results reveal that 69.0% of "SWP" is predicted by the independent variables (R2 = 0.690), "Anthropogenic" contributes by increasing SWP (ß = 0.471), while "Nature" decreases the concentration of SWP (ß = -0.523), which indicates the polluting parameters in the water. The variables "Anthropogenic" (ß = -0.351) and "SWP" (ß = -0.265) lower the quality of "Ecological Integrity". This variable must be managed through soil conservation measures for the benefit of water security. This study has been able to identify and quantify the variables that increase contaminant concentration and decrease ecological integrity, providing a promising methodology that facilitates protection and correction measures to guarantee water safety.

Influence of Microcystis sp. and freshwater algae on pH: Changes in their growth associated with sediment.

Samples from two reservoirs with eutrophication problems, located in Pontevedra and Ourense (Northwestern Spain), were cultured, along with a third crop from a reservoir with no problems detected in Ourense (Northwestern Spain). The samples were grown under the same conditions (with an average temperature of 21 ± 2 °C, and a 3000 lux light intensity) in triplicate, and their growth, absorbance and pH were studied. High correlation values were obtained for pH and cellular growth (R2 ≥ 95%). The water from Salas showed the greatest microalgal growth (0.15 × 106 cells/ml to 31.70 × 106 cells/ml of Microcystis sp. for the last day of culturing) and the greatest increase in pH (5.72-9.02). In all the cultures studied here, the main species that reproduced was Microcystis sp., which can produce neurotoxins and hepatotoxins. In addition, water samples were cultured with sediments of their own reservoir and with others to observe their evolution. The sediments studied in this case were rich in biotites, which can lead phosphate to be a limiting factor for phytoplankton due to the formation and sedimentation of insoluble salts of ferric phosphate. In crops grown with sediments from the Salas reservoir, actinobacteria developed which can inhibit microalgal growth. The study of the growth of cyanobacteria and possible methods of inhibiting them directly concerns the quality of water and its ecosystems, avoiding pollution and impact on ecosystems.

Assessment of water quality in eutrophized water bodies through the application of indexes and toxicity.

It is essential to have tools that can be used to diagnose water resources. For this reason, this study sets out on the one hand to assess water quality in three reservoirs in Spain (Salas, A Baxe and Conchas) with Cyano-Habs problems through the application of water quality indexes: The National Sanitation Foundation Water Quality Index (NFSWQI), the General Quality Index (GQI), the Trophic State Index (TSI), and the Trophic Contamination Index (ICOTRO). On the other hand, it seeks to learn how parameters such as nitrogen and phosphorus influence the presence of cyanotoxin, specifically Microcystis aeruginosa. To that end, samples from the three reservoirs are cultured and physical-chemical parameters and the toxicity of the water are measured. The results show that Salas reservoir has the worst water quality rating (GQI is bad and NFSWQI medium), while As Conchas and A Baxe obtain very good figures for NFSWQI. This contrasts with the data obtained via the TSI of moderately eutrophic conditions for all three reservoirs, and hypereutrophic levels for As Conchas and A Baxe downstream. On the other hand, the toxicity analysis shows levels of 1.12 ±â€¯0.06 µg/l microcystin-LR (MC-LR) for As Conchas, 0.64 ±â€¯0.04 µg/l MC-LR for Salas, and 1.24 ±â€¯0.05 µg/l MC-LR for A Baxe, of which 20% corresponds to free MC-LR. This study finds that nitrogen is the parameter that most favors the production of MC-LR. We conclude that the eutrophication indexes are more reliable when studying the presence of cyanobacteria. Furthermore, nitrogen and phosphorous are the most significant parameters in this regard. They are taken into account in the quality indices (GQI, NFSWI), but they are not sufficiently representative. It is recommended as a future line of research that water quality indices be adapted or designed to incorporate eutrophication levels and even water toxicity.

Hydrothermal Carbonization and Pellet Production from Egeria densa and Lemna minor.

Biofuels are seen as a potential option for mitigating the effects of fossil fuel use. On the other hand, nutrient pollution is accelerating eutrophication rates in rivers, lakes, and coastal waters. Harvesting aquatic plants to produce biofuels could mitigate this problem, though it is important to attack the problem at source, mainly as regards the contribution of nutrients. For the first time, solid biofuels were obtained in the forms of carbon and pellets from the aquatic plants Egeria densa, which is classed as an invasive plant under the Spanish Catalogue of Exotic Invasive Species, and Lemna minor, both of which can be found in the Umia River in north-west Spain. The essential oils and macro- and microelements present in both these plants were also extracted and analyzed. The higher heating values (HHVs) of the carbon products obtained ranged from 14.28 to 17.25 MJ/kg. The ash content ranged from 22.69% to 49.57%. The maximum yield obtained for biochar for Egeria densa at 200 °C was 66.89%. Temperature significantly affects solid hydrochar yield. The HHVs of the pellets obtained ranged from 11.38 to 13.49 MJ/kg. The use of these species to obtain biofuels through hydrothermal carbonization (HTC) and pellets is a novel and effective approach that will facilitate the removal of nutrients that cause eutrophication in the Umia River. The elements extracted show that harvesting these plants will help to remove excessive nutrients from the ecosystem.