Development of an ANN-based tool for sediment management at run-of-river reservoirs

Introduction Reservoirs are needed for many fundamental tasks like agriculture, drinking water supply, flood protection, and energy production. For each of the listed demands, sustainable management of the reservoir is of great importance in designing the storage volume of water. However, sedimentation threatens this storage volume worldwide (Schleiss et al., 2016). In addition, a reduced retention volume due to sedimentation might also increase the danger potential of floods (Reisenbüchler et al., 2019). Numerical models are widely accepted for designing new reservoirs and dams or to develop management strategies at existing dams to counteract sedimentation (Annandale et al., 2016). Such models can accurately represent reality and give reliable predictions. However, accurate and complex (e.g. two- or three-dimensional) models require great computational efforts. Furthermore, achieving an optimal design or evaluating different management strategies requires multiple long-term simulations for different scenarios. In that case, simplified 1D models were still applied. To provide an alternative, our work presents the application of a data-driven method for predicting bed level change along a river section including a hydropower plant.     «

Introduction Reservoirs are needed for many fundamental tasks like agriculture, drinking water supply, flood protection, and energy production. For each of the listed demands, sustainable management of the reservoir is of great importance in designing the storage volume of water. However, sedimentation threatens this storage volume worldwide (Schleiss et al., 2016). In addition, a reduced retention volume due to sedimentation might also increase the danger potential of floods (Reisenbüc...     »