Accurate segmentation of river water in close-range Remote Sensing (RS) images is vital for efficient environmental monitoring and management. However, this task poses significant difficulties due to the dynamic nature of water, which exhibits varying colors and textures reflecting the sky and surrounding structures along the riverbanks. This study addresses these complexities by evaluating and comparing several well-known deep-learning (DL) techniques on four river scene datasets. To achieve this, we fine-tuned the recently introduced "Segment Anything Model" (SAM) along with popular DL segmentation models such as U-Net, DeepLabV3+, LinkNet, PSPNet, and PAN, all using ResNet50 pre-trained on ImageNet as a backbone. Experimental results highlight the diverse performances of these models in river water segmentation. Notably, fine-tuned SAM demonstrates superior performance, followed by U-Net _(ResNet50) , despite their higher computational costs. In contrast, PSPNet _(ResNet50) , while less effective, proves to be the most efficient in terms of execution time. In addition to these findings, we introduce a novel river water segmentation dataset, LuFI-RiverSnap. v 1 (Dataset link), characterized by a more diverse range of scenes and accurate masks compared to existing datasets. To facilitate reproducible research in remote sensing and computer vision, we release the implementations of the fine-tuned SAM model (Code link). The findings from this research, coupled with the presented dataset and the accuracy achieved by fine-tuned SAM segmentation, can support tracking river changes, understanding river water level trends, and exploring river ecosystem dynamics. These can also provide valuable insights for practitioners and researchers seeking models tailored to specific image characteristics with practical means in disaster risk reduction, such as rapid assessments of inundations during floods or automatic extractions of gauge data in watersheds.

The present article presents results of a laboratory study on the assessment of erosion patterns around a hydrodynamic transparent offshore foundation exposed to combined waves and currents. The model tests were conducted under irregular, long-crested waves in a scale of 1:30 in a wave-current basin. A terrestrial 3D laser scanner was used to acquire data of the sediment surface around the foundation structure. Tests have been conducted systematically varying from wave- to current-dominated conditions. Different volume analyzing methods are introduced, which can be related for any offshore or coastal structure to disclose physical processes in complex erosion patterns. Empirical formulations are proposed for the quantification of spatially eroded sediment volumes and scour depths in the near-field and vicinity of the structure. Findings from the present study agree well with in-situ data stemming from the field. Contrasting spatial erosion development between experimental and in-situ data determines a stable maximum of erosion intensity at a distance of 1.25 A, 1.25 times the structure’s footprint A, as well as a global scour extent of 2.1–2.7 A within the present study and about 2.7–2.8 A from the field. By this means, a structure-induced environmental footprint as a measure for erosion of sediment affecting marine habitat is quantified.

This study aims to improve the design of scour protection around offshore wind turbine monopiles, as well as future-proofing them against the impacts of climate change. A series of large-scale experiments have been performed in the context of the European HYDRALAB-PLUS PROTEUS (Protection of offshore wind turbine monopiles against scouring) project in the Fast Flow Facility in HR Wallingford. These experiments make use of state of the art optical and acoustic measurement techniques to assess the damage of scour protections under the combined action of waves and currents. These novel PROTEUS tests focus on the study of the grading of the scour protection material as a stabilizing parameter, which has never been done under the combined action of waves and currents at a large scale. Scale effects are reduced and, thus, design risks are minimized. Moreover, the generated data will support the development of future scour protection designs and the validation of numerical models used by researchers worldwide. The testing program objectives are: (i) to compare the performance of single-layer wide-graded material used against scouring with current design practices; (ii) to verify the stability of the scour protection designs under extreme flow conditions; (iii) to provide a benchmark dataset for scour protection stability at large scale; and (iv) to investigate the scale effects on scour protection stability.

This research advances the understanding of jacket-type platform induced local and global erosion and deposition processes for combined wave–current conditions. To this end, a laboratory study was carried out comparing the equilibrium scour depth for two structural designs that are differentiated in the geometrical distance of the structure’s lowest node to the seabed. Measurements of local scour depths over time have been conducted with echo sounding transducers. An empirical approach is proposed to predict the final scour depths as a function of the node distance to the seabed. Additionally, 3D laser scans have been performed to obtain the digital elevation model of the surrounding sediment bed. Novel methodologies were developed to describe and easily compare the relative volume change of the sediment bed per surface area due to structure–seabed interaction, enabling spatial analyses of highly complex erosion and deposition patterns. The seabed sediment mobility around the structure is found to be highly sensitive to a change in node distance. The decrease of the node distance results in a higher erosion depth of sediment underneath the structure of up to 26%, especially for current-dominated conditions, as well as an increased deposition of sediment downstream of the structure over a distance of up to 6.5 times the footprint length. The results of this study highlight the requirement to consider the interaction of the structure with the surrounding seabed within the design process of offshore structures, to mitigate potential impacts on the marine environment stemming from the extensive sediment displacement and increased sediment mobility.