Daily Suspended Sediment Prediction Using Seasonal Time Series and Artificial Intelligence Techniques

Estimating the amount of suspended sediment in rivers correctly is important due to the adverse impacts encountered during the design and maintenance of hydraulic structures such as dams, regulators, water channels and bridges. The sediment concentration and discharge currents have usually complex relationship, especially on long term scales, which can lead to high uncertainties in load estimates for certain components. In this paper, with several data-driven methods, including two types of perceptron support vector machines with radial basis function kernel (SVM-RBF), and poly kernel learning algorithms (SVM-PK), Library SVM (LibSVM), adaptive neuro-fuzzy (NF) and statistical approaches such as sediment rating curves (SRC), multi linear regression (MLR) are used for forecasting daily suspended sediment concentration from daily temperature of water and streamflow in the river. Daily data are measured at Augusta station by the US Geological Survey. 15 different input combinations (1 to 15) were used for SVM-PK, SVM-RBF, LibSVM, NF and MLR model studies. All approaches are compared to each other according to three statistical criteria; mean absolute errors (MAE), root mean square errors (RMSE) and correlation coefficient (R). Of the applied linear and nonlinear methods, LibSVM and NF have good results, but LibSVM generates a slightly better fit under whole daily sediment values.