Suchergebnisse

AbstractDespite the substantial impact of rivers on the global marine litter problem, riverine litter has been accorded inadequate consideration. Therefore, our objective was to detect riverine litter by utilizing middle-scale multispectral satellite images and machine learning (ML), with the Tisza River (Hungary) as a study area. The Very High Resolution (VHR) images obtained from the Google Earth database were employed to recognize some riverine litter spots (a blend of anthropogenic and natural substances). These litter spots served as the basis for training and validating five supervised machine-learning algorithms based on Sentinel-2 images [Artificial Neural Network (ANN), Support Vector Classifier (SVC), Random Forest (RF), Naïve Bays (NB) and Decision Tree (DT)]. To evaluate the generalization capability of the developed models, they were tested on larger unseen data under varying hydrological conditions and with different litter sizes. Besides the best-performing model was used to investigate the spatio-temporal variations of riverine litter in the Middel Tisza. According to the results, almost all the developed models showed favorable metrics based on the validation dataset (e.g., F1-score; SVC: 0.94, ANN: 0.93, RF: 0.91, DT: 0.90, and NB: 0.83); however, during the testing process, they showed medium (e.g., F1-score; RF:0.69, SVC: 0.62; ANN: 0.62) to poor performance (e.g., F1-score; NB: 0.48; DT: 0.45). The capability of all models to detect litter was bounded to the pixel size of the Sentinel-2 images. Based on the spatio-temporal investigation, hydraulic structures (e.g., Kisköre Dam) are the greatest litter accumulation spots. Although the highest transport rate of litter occurs during floods, the largest litter spot area upstream of the Kisköre Dam was observed at low stages in summer. This study represents a preliminary step in the automatic detection of riverine litter; therefore, additional research incorporating a larger dataset with more representative small litter spots, as well as finer spatial resolution images is necessary.

The development of point-bars and bank erosion are critical near-bank processes, as they indicatethe sediment and hydraulic regime of a river system, thus, they refer to the equilibrium conditions ofa channel. However, throughout history, rivers have been modified for various benefits which changethe development of point-bars and the rate of bank erosion. In the Lower Tisza River (Hungary), riverregulations influenced the channel and floodplain development, altering the natural fluvial processes.The aim of the research was to determine the rate of near-bank processes and to make trajectory forfuture river evolution to support future engineering works. The bank erosion and point-bar developmentat human-influenced and freely meandering sections of the Tisza River were monitored since 2011.Behind a collapsed revetment, the bank erosion rate was 0.6 m/y, while at a freely meandering section itwas 2.3 m/y. The studied point-bars are located in revetted and freely meandering sections. Their surfaceeroded within the period. These intensive erosional processes refer to an incising meandering channel,which must be considered during future planning of in-channel structures (e.g. revetments, bridges),thus, geomorphic methods must be considered in any river engineering scheme.

Sediment transport is a vital component in hydrological and fluvial geomorphological studies, however, the temporal and spatial changes in sediment fluxes, and the efficiency of bedload samplers are rarely analysed, as bedload measurements are quite difficult. The aim of the present study is to measure the bedload transport of the sand-bedded Maros River (Hungary) at low stages using the Helley-Smith bedload sampler. In order to understand the variability in the bedload transport, the water stage and discharge across the channel section were also measured. The variability of the bedload was caused by an active in-channel bar and translational sediment pulses. The created bedload transport rating curve could be applied just below 300 m3/s water discharge thus further measurements are needed to evaluate the bedload transport of higher discharges.

Abstract
Background
Precisely predicting the water levels of rivers is critical for planning and supporting flood hazard and risk assessments and maintaining navigation, irrigation, and water withdrawal for urban areas and industry. In Hungary, the water level of rivers has been recorded since the early nineteenth century, and various water level prediction methods were developed. The Discrete Linear Cascade Model (DLCM) has been used since 1980s. However, its performance is not always reliable under the current climate-driven hydrological changes. Therefore, we aimed to test machine learning algorithms to make 7-day ahead forecasts, choose the best-performing model, and compare it with the actual DLCM.

Results
According to the results, the Long Short-Term Memory (LSTM) model provided the best results in all time horizons, giving more precise predictions than the Baseline model, the Linear or Multilayer Perceptron Model. Despite underestimating water levels, the validation of the LSTM model revealed that 68.5‒76.1% of predictions fall within the required precision intervals. Predictions were relatively accurate for low (≤ 239 cm) and flood stages (≥ 650 cm), but became less reliable for medium stages (240–649 cm).

Conclusions
The LSTM model provided better results in all hydrological situations than the DLCM. Though, LSTM is not a novel concept, its encoder–decoder architecture is the best option for solving multi-horizon forecasting problems (or "Many-to-Many" problems), and it can be trained effectively on vast volumes of data. Thus, we recommend testing the LSTM model in similar hydrological conditions (e.g., lowland, medium-sized river with low slope and mobile channel) to get reliable water level forecasts under the rapidly changing climate and various human impacts.

Graphical Abstract