No abstract

10The complex multi-directional interactions between hydrological, biological and fluvial processes govern the formation and evolution of river landscapes. In this context, as key geomorphological agents, riparian trees are particularly important in trapping sediment and constructing distinct landforms, which subsequently evolve to larger ones. The primary objective of this paper is to experimentally investigate the scour/deposition patterns around different forms of individual vegetation elements. Flume experiments were conducted in which the scour patterns around different representative forms of individual in-stream obstructions (solid cylinder, hexagonal array of circular cylinders, several forms of emergent and submerged vegetation) were monitored by means of a high-resolution laser scanner. The three dimensional scour geometry around the simulated vegetation elements was quantified and discussed based on the introduced dimensionless morphometric characteristics. The findings reveal that the intact vegetation forms generated two elongated scour holes at the downstream with a pronounced ridge. For the impermeable form of the plant, the scour got localized, more deposition was detected within the monitoring zone, and the distance between the obstruction and deposition zone became shorter. It is also shown that with the effect of bending and the subsequent decrease of the projected area of the plant and the increase of bulk volume, the characteristic scour values decrease compared to the intact version, and the scour zone obtains a more elongated form and expands in the downstream direction.

3D scene classification has become an important research field in photogrammetry, remote sensing, computer vision and robotics with the widespread usage of 3D point clouds. Point cloud classification, called semantic labeling, semantic segmentation, or semantic classification of point clouds is a challenging topic. Machine learning, on the other hand, is a powerful mathematical tool used to classify 3D point clouds whose content can be significantly complex. In this study, the classification performance of different machine learning algorithms in multiple scales was evaluated. The feature spaces of the points in the point cloud were created using the geometric features generated based on the eigenvalues of the covariance matrix. Eight supervised classification algorithms were tested in four different areas from three datasets (the Dublin City dataset, Vaihingen dataset and Oakland3D dataset). The algorithms were evaluated in terms of overall accuracy, precision, recall, F1 score and process time. The best overall results were obtained for four test areas with different algorithms. Dublin City Area 1 was obtained with Random Forest as 93.12%, Dublin City Area 2 was obtained with a Multilayer Perceptron algorithm as 92.78%, Vaihingen was obtained as 79.71% with Support Vector Machines and Oakland3D with Linear Discriminant Analysis as 97.30%.

Abstract:The most significant morphological property of a river is the meandering process, which is dominated and governed by hydraulic, hydrologic and topographic characteristics of the river and its drainage area. It is possible to obtain reliable data on river morphology in the long term by using remotely sensed data. In this study the Filyos River, located at the Western Black Sea region of Turkey, has been selected as the study area to show the capabilities of remote sensing technology and to define the appropriate techniques for achieving the most reliable information on the river morphology by monitoring the meandering processes. The findings of the study indicate that remotely sensed data can be used successfully in defining some basic characteristics of the meandering process on rivers.

No abstract