In this study, a new concept was proposed for hydromorphological changes in fluvial rivers,
where an artificial neural network (ANN) model has been integrated into a hydromorphological
model system. For this purpose, the open-source system TELEMAC-MASCARET has been
applied to simulate evolution of the bed in a 180° channel bend. The simulated results are used
as input-data into ANN model to obtain an ANN-based approximator. According to the
proposed concept, the sediment transport module SISYPHE is then replaced by an ANN model
that is coupled with either the 2D or 3D flow models. At each coupling time period, the required
hydrodynamic variables calculated by TELEMAC-2D or -3D are sent to the ANN based
approximator to calculate the new bed level change. To evaluate the quality of the proposed
model predictions, a comparative study has been carried out by estimating several parameters
that describe the errors associated with the model in terms of statistical measures of goodnessof-
fit between the estimated bed change and TELEMAC-MASCARET simulation. The results
indicated that the proposed model would simulate and predict the morphological bed level
changes satisfactorily.
«
In this study, a new concept was proposed for hydromorphological changes in fluvial rivers,
where an artificial neural network (ANN) model has been integrated into a hydromorphological
model system. For this purpose, the open-source system TELEMAC-MASCARET has been
applied to simulate evolution of the bed in a 180° channel bend. The simulated results are used
as input-data into ANN model to obtain an ANN-based approximator. According to the
proposed concept, the sediment transport module SI...
»