USABILITY OF ARTIFICIAL NEURAL NETWORKS FOR SEDIMENT ESTIMATION


Author(s): Ahmet Alperen Acar1, Meral Buyukyildiz2
  • 1. Barış Mah. Halide Edip Adıvar Cad., DSİ 13. Bölge Müd., 131.Şube Müd. Antalya, Turkey
  • 2. Department of Civil Engineering, Konya Technical University, Turkey

Abstract: Sediment estimation is very important as water resources projects with high costs cause the economic life of projects to decrease more quickly. In order to prevent the decrease in the economic life of the dam reservoirs and to reduce the sedimentation in the dam reservoirs, it is also necessary to determine the sediment carried by the river. Recently Artificial Neural Network (ANN) is widely used to solve the complex problems such as sediment. In this study, the flow (m3/sec) and sediment (ton/day) data of the Söğütlühan Observation Station during the 1994-2011 periods in the Kızılırmak Basin are used for the sediment estimation. The results of ANN models and sediment rating curve method were compared. As a result of the comparison, it was seen that ANN models were more successful than sediment rating curve for sediment estimation.