Artificial neural network for modelling the sediments accumulation in Es-Saada reservoir (North-Western Algeria)
by Mustapha Sidi Adda; Djilali Yebdri; Djilali Baghdadi; Sarita Gajbhiye Meshram
International Journal of Hydrology Science and Technology (IJHST), Vol. 17, No. 1, 2024

Abstract: Sediment deposition represents an important aspect of dam reservoir exploitation and management, as it relates to several operational and environmental problems. This study aimed to model the spatiotemporal evolution of the sediment accumulation in the Es-Saada reservoir (North-Western Algeria) using an artificial neural network (ANN) under low data conditions. The ANN model calibration was applied to the chronological period between the bathymetric surveys in 1986 and 2000, and the model verification was performed using data from a third survey conducted in 2003. The simulation of the reservoir bed presented acceptable results compared to the measured data (mean error of 7.76%). The model can provide predictive capacity curve for an average gap of 0.068 to the real curve, with a signification of 93.2%. It would be concluded that using determinist models for predicting sediment accumulation in reservoirs is complicated and needs all system details, while the application of ANN presents an adequate and uncomplicated method for predicting sediment distribution in dam reservoirs and also reservoir volume reduction in an approximate way.

Online publication date: Fri, 01-Dec-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Hydrology Science and Technology (IJHST):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com