Taher Rajaee - Associate Prof., Dept. of Civil Eng., Qom University, Qom, Iran
Seyed Ahmad Mirbagheri - Associate Prof. Dept. of Civil Eng., K.N.TOOSI University of Technology
Mohammad Zounemat-Kermani - Dept. of Water Eng., Shahid Bahonar University of Kerman, Iran
Vahid Nourani

The prediction of sediment load and its variability in rivers is a component of water resources and environmental engineering and management of infrastructures. Suspended sediment concentration (SSC) prediction in a gauging station in the USA by artificial neural networks (ANNs), Neuro-Fuzzy (NF) and conventional sediment rating curve (SRC) models were investigated in this research. The models were trained using daily river discharge and SSC data belonging to Little Black River gauging station in the USA. The suspended sediment concentration predicted by the NF model was in satisfactory agreement with the measured data. The cumulative suspended sediment load estimated by ANN and NF models is closer to the actual data than the SRC method. In general, the results illustrate that the NF model produced better performance in SSC prediction in various evaluations than the ANN and SRC models.

Artificial Neural Networks, Neuro-Fuzzy, Sediment rating curve, Suspended sediment prediction