Title: Suspended sediment estimation using regression and artificial neural network models: Kebir watershed, northeast of Algeria, North Africa

Authors: Amina Amamra; Kamel Khanchoul; Saeid Eslamian; Soraya Hadj Zobir

Addresses: Laboratory of Soils and Sustainable Development, Department of Biology, Badji Mokhtar University-Annaba, P.O. Box 12, 23000 Annaba, Algeria ' Laboratory of Soils and Sustainable Development, Department of Geology, Badji Mokhtar University-Annaba, P.O. Box 12, 23000 Annaba, Algeria ' Department of Water Engineering, College of Agriculture, Isfahan University of Technology, Isfahan 8145683111, Iran ' Laboratory of Soils and Sustainable Development, Department of Geology, Badji Mokhtar University-Annaba, P.O. Box 12, 23000 Annaba, Algeria

Abstract: The focus of this research was to identify potential equivalences between artificial neural networks and statistical regression and to verify these equivalences when applied to modelling sediment loads in the Kebir river. The use of feed-forward backpropagation neural networks such as MLP and LM were studied by applying relationship stream flow-sediment discharge data and geomorphology watershed parameters. Daily based water and sediment discharge were used as inputs for sediment rating curve and ANNs. In the present study the models were adopted by changing numbers of neuron in hidden layers and epoch. Results have shown that the ANN models were superior in reproducing sediment discharge compared to SRC. The findings further have suggested that LM could provide the most accurate estimates of sediment discharge, (R² and EF of 0.94) compared to SRC had lower values of R² and EF (0.89, 0.88), and resulted in underestimations of sediment discharge (−15%).

Keywords: sediment discharge; geomorphology; neural network; sediment rating curve; SRC; Kebir river.

DOI: 10.1504/IJHST.2018.095526

International Journal of Hydrology Science and Technology, 2018 Vol.8 No.4, pp.352 - 371

Received: 01 Mar 2016
Accepted: 20 Jul 2016
Published online: 09 Oct 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article