Search

This study emphasizes the importance of accurate calibration in sediment transport models and highlights the transformative role of artificial intelligence (AI), specifically machine learning, in improving accuracy and computational efficiency. Extensive experiments were carried out in the Riba-Roja reservoir, which is located in the northeastern Iberian Peninsula. The accumulated sediment volume (ASV) curve was used to calibrate these experiments. The optimal ASV curve was found to be very close to the experimental data, with only minor differences in upstream areas. The results revealed a consistent rate of sediment transport and settling. Furthermore, the study investigated the capabilities of deep neural networks (DNNs) in predicting ASV curves and observing variable performance. In essence, the study highlights AI's potential for enhancing sediment transport models. • The study underscores the value of AI in enhancing sediment transport model calibration. • The simulations revealed accurate results, with minor discrepancies in upstream regions. • The DNNs, demonstrated reliable predictive capabilities in forecasting ASV curves. • AI, coupled with Monte Carlo method, reduces sediment model computation time. [ABSTRACT FROM AUTHOR]

Upstream from a dam reservoir, river hydrodynamics may be directly changed by temporary inundation driven by the reservoir. This triggers morphological river changes which may additionally modify the initial hydrodynamics, even at the time when backwater inundation does not occur (indirect effects of backwater). We verified these hypotheses, applying two-dimensional hydraulic modelling of flood flows to a section of the mountainous Dunajec River upstream from the Czorsztyn Reservoir. The modelling was performed for small, medium and large floods, and hydraulic conditions were compared between the scenarios with lacking and maximum backwater inundation and between the river reaches subjected to backwater inundation and unaffected by backwater fluctuations. Direct effects of reservoir level fluctuations were limited to the reach subjected to backwater inundation during floods and comprised: significantly increased water depth and decreased flow velocity and bed shear stress in the channel and on the floodplain, as well as a re-established hydrological connectivity between the channel and floodplain during small and medium floods. Indirect effects of backwater inundation reflected channel widening and bed aggradation that triggered a positive feedback with changes in hydrodynamics, mostly by reducing the velocity of flood flows in the channel zone. These latter changes occurred on a longer distance upstream from the reservoir than the backwater reach itself, and they modified the river hydrodynamics even when backwater inundation did not occur. We propose a conceptual model which indicates that changes of mountain rivers upstream from dam reservoirs are driven by modified hydrodynamics and lead to different morphological adjustments than those induced by waters underloaded with sediment downstream from dams. Changes in hydrodynamics and the associated morphological and sedimentary adjustments of mountain rivers recorded upstream from dam reservoirs may locally mitigate impacts of channelization and channel incision on riverine and riparian ecosystems of these rivers. Unlabelled Image • Effects of backwater inundation on river hydrodynamics upstream from dam reservoir were investigated. • Hydraulic modelling of flood flows in backwater and control reaches and with/without backwater inundation was performed. • Backwater inundation increases water depth and decreases velocity and bed shear stress of the channel and floodplain flows. • Backwater-induced morphological river changes additionally modify river hydrodynamics. • Conceptual model of hydrodynamics–morphology adjustments downstream and upstream of a dam reservoir was presented. [ABSTRACT FROM AUTHOR]