Although plastic pollution is one of the most noteworthy environmental issues nowadays, there is still a knowledge gap in terms of monitoring the spatial distribution of plastics, which is needed to prevent its negative effects and to plan mitigation actions. Unmanned Aerial Vehicles (UAVs) can provide suitable data for mapping floating plastic, but most of the methods require visual interpretation and manual labeling. The main goals of this paper are to determine the suitability of deep learning algorithms for automatic floating plastic extraction from UAV orthophotos, testing the possibility of differentiating plastic types, and exploring the relationship between spatial resolution and detectable plastic size, in order to define a methodology for UAV surveys to map floating plastic. Two study areas and three datasets were used to train and validate the models. An end-to-end semantic segmentation algorithm based on U-Net architecture using the ResUNet50 provided the highest accuracy to map different plastic materials (F1-score: Oriented Polystyrene (OPS): 0.86; Nylon: 0.88; Polyethylene terephthalate (PET): 0.92; plastic (in general): 0.78), showing its ability to identify plastic types. The classification accuracy decreased with the decrease in spatial resolution, performing best on 4 mm resolution images for all kinds of plastic. The model provided reliable estimates of the area and volume of the plastics, which is crucial information for a cleaning campaign.

Digital elevation model (DEM) has been frequently used for the reduction and management of flood risk. Various classification methods have been developed to extract DEM from point clouds. However, the accuracy and computational efficiency need to be improved. The objectives of this study were as follows: (1) to determine the suitability of a new method to produce DEM from unmanned aerial vehicle (UAV) and light detection and ranging (LiDAR) data, using a raw point cloud classification and ground point filtering based on deep learning and neural networks (NN); (2) to test the convenience of rebalancing datasets for point cloud classification; (3) to evaluate the effect of the land cover class on the algorithm performance and the elevation accuracy; and (4) to assess the usability of the LiDAR and UAV structure from motion (SfM) DEM in flood risk mapping. In this paper, a new method of raw point cloud classification and ground point filtering based on deep learning using NN is proposed and tested on LiDAR and UAV data. The NN was trained on approximately 6 million points from which local and global geometric features and intensity data were extracted. Pixel-by-pixel accuracy assessment and visual inspection confirmed that filtering point clouds based on deep learning using NN is an appropriate technique for ground classification and producing DEM, as for the test and validation areas, both ground and non-ground classes achieved high recall (>0.70) and high precision values (>0.85), which showed that the two classes were well handled by the model. The type of method used for balancing the original dataset did not have a significant influence in the algorithm accuracy, and it was suggested not to use any of them unless the distribution of the generated and real data set will remain the same. Furthermore, the comparisons between true data and LiDAR and a UAV structure from motion (UAV SfM) point clouds were analyzed, as well as the derived DEM. The root mean square error (RMSE) and the mean average error (MAE) of the DEM were 0.25 m and 0.05 m, respectively, for LiDAR data, and 0.59 m and –0.28 m, respectively, for UAV data. For all land cover classes, the UAV DEM overestimated the elevation, whereas the LIDAR DEM underestimated it. The accuracy was not significantly different in the LiDAR DEM for the different vegetation classes, while for the UAV DEM, the RMSE increased with the height of the vegetation class. The comparison of the inundation areas derived from true LiDAR and UAV data for different water levels showed that in all cases, the largest differences were obtained for the lowest water level tested, while they performed best for very high water levels. Overall, the approach presented in this work produced DEM from LiDAR and UAV data with the required accuracy for flood mapping according to European Flood Directive standards. Although LiDAR is the recommended technology for point cloud acquisition, a suitable alternative is also UAV SfM in hilly areas.

Surface water maps are essential for many environmental applications. Waterbody delineation from satellite images remains a challenging task due to sensor limitations, the presence of clouds, the low albedo surfaces in urban areas, topographic, and atmospheric conditions. In this paper, a model based on the Supported Vector Machine (SVM) classifier was adopted for waterbody extraction from Sentinel-2, Landsat 8 Operational Land Imager (OLI) and RapidEye satellite images. As well, the accuracy of two other sources (OpenStreetMapping (OSM) and Military Geographic Institute (MGI)) was tested. The free images from Sentinel-2 and Landsat 8 OLI were more accurate (Kappa (KHAT):0.89, 0.88) data sources than commercial RapidEye images (KHAT: 0.79). Regarding the performance between Sentinel-2 and Landsat 8 OLI, Sentinel-2 obtained the most accurate results (overall accuracy 94.49 vs. 94.17, commission error 1.34 vs. 1.87). Due to the variable spatial resolution of OSM and MGI data, it was not possible to detect small waterbodies with these sources, and therefore high values of omission error and a strong underestimation of the area of surface water were obtained. This study demonstrates the suitability of free images for mapping and monitoring of surface waterbodies, including small water bodies.

Fire risk management starts with an assessment of the most flammable places. In this paper, identification, classification and mapping of forest fire risk is completed with an aim of reducing the ratio and ecological damage caused by the...

Water scarcity and quality deterioration, driven by rapid population growth, urbanization, and intensive industrial and agricultural activities, emphasize the urgency for effective water management. This study aims to develop a model to comprehensively monitor various water quality parameters (WQP) and evaluate the feasibility of implementing this model in real-world scenarios, addressing the limitations of conventional in-situ sampling. Thus, a comprehensive model for monitoring WQP was developed using a 38-year dataset of Landsat imagery and in-situ data from the Water Information System of Europe (WISE), employing Back-Propagated Artificial Neural Networks (ANN). Correlation analyses revealed strong associations between remote sensing data and various WQPs, including Total Suspended Solids (TSS), chlorophyll-a (chl-a), Dissolved Oxygen (DO), Total Nitrogen (TN), and Total Phosphorus (TP). Optimal band combinations for each parameter were identified, enhancing the accuracy of the WQP estimation. The ANN-based model exhibited very high accuracy, particularly for chl-a and TSS (R² > 0.90, NRMSE < 0.79%), surpassing previous studies. The independent validation showcased accurate classification for TSS and TN, while DO estimation faced challenges during high variation periods, highlighting the complexity of DO dynamics. The usability of the developed model was successfully tested in a real-case scenario, proving to be an operational tool for water management. Future research avenues include exploring additional data sources for improved model accuracy, potentially enhancing predictions and expanding the model’s utility in diverse environmental contexts.

Water bodies are among most sensitive ecological environments. In order to ensure good water quality and establish framework for their protection European Parliament was adopted the Water Framework Directive (WFD) (Directive 2000/60/EC). The biological, hydro morphological and physic chemical quality parameters which are relevant for assessment of ecological status of water body are defined in Annex V of WFD. Traditionally, quality of surface water bodies are monitored by in situ measurements resulting in low spatial and temporal resolution of historical data. Remote sensing has great potential for monitoring and identification of water bodies over large scale regions in a more effective and efficient manner. In order to provide reliable monitoring of water quality, surface reflection derived by multispectral sensors need to be integrated with in situ measurements. Relationship between remote sensing and in situ data is usually modeled by using empirical, machine learning or deep learning algorithms. In this study, a 4-year (2013-2016) result of in situ monitoring of surface water bodies in Serbia are used for calibration and validation of algorithm for water quality monitoring based on Landsat 8 satellite image. The Turbidity, Suspending Sediments, Total Phosphorus and Total Nitrogen (physic chemical parameters) in region of Vojvodina, Republic of Serbia are monitored. The Neuron Networks and Supported Vector Machine are used to analyzing correlation between in situ measurements and Landsat 8 atmospherically corrected satellite images. Feature more, capabilities of Landsat 8 are compared with Sentinel 2 images (2-years, 2015-2016). In situ data are provided by Agency for environment protection of Serbia.