Modeling of streamflow- suspended sediment load relationship by adaptive neuro-fuzzy and artificial neural network approaches (Case study: Dalaki River, Iran)

Abstract

Modeling of stream flow–suspended sediment relationship is one of the most studied topics in hydrology due to its<br />essential application to water resources management. Recently, artificial intelligence has gained much popularity owing to<br />its application in calibrating the nonlinear relationships inherent in the stream flow–suspended sediment relationship. This<br />study made us of adaptive neuro-fuzzy inference system (ANFIS) techniques and three artificial neural network<br />approaches, namely, the Feed-forward back-propagation (FFBP), radial basis function-based neural networks (RBF),<br />geomorphology-based artificial neural network (GANN) to predict the streamflow suspended sediment relationship. To<br />illustrate their applicability and efficiency,, the daily streamflow and suspended sediment data of Dalaki River station in<br />south of Iran were used as a case study. The obtained results were compared with the sediment rating curve (SRC) and<br />regression model (RM). Statistic measures (RMSE, MAE, and R2) were used to evaluate the performance of the models.<br />From the results, adaptive neuro-fuzzy (ANFIS) approach combined capabilities of both Artificial Neural Networks and<br />Fuzzy Logic and then reflected more accurate predictions of the system. The results showed that accuracy of estimations<br />provided by ANFIS was higher than ANN approaches, regression model and sediment rating curve. Additionally, relating<br />selected geomorphologic parameters as the inputs of the ANN with rainfall depth and peak runoff rate enhanced the<br />accuracy of runoff rate, while sediment loss predictions from the watershed and GANN model performed better than the<br />other ANN approaches together witj regression equations in Modeling of stream flow–suspended sediment relationship.