Cross-shore sediment transport estimation using fuzzy inference system in the swash zone

The interactions between fluid and sediment in the swash zone dominate the erosion or accretion of the beach, and they act as boundary conditions for nearshore hydrodynamic and morphodynamic models. Thus, the evaluation of sediment transport is of particular importance for many coastal processes and the design of coastal structures. In this paper, unlike conventional approaches, Fuzzy Inference System (FIS) and Adaptive-Network-Based Fuzzy Inference System (ANFIS) methods are used for the prediction and simulation of cross-shore sediment transport in the swash zone. The ANFIS and FIS are established using the free stream velocity time series, Shields parameter and antecedent sediment data. Statistical measures were used to evaluate the performance of the models. The cross-shore sediment transport rate and swash velocity time series for the swash experiments of Masselink and Hughes (1998) were used as case studies. Predicated on numerical results, it is found that the ANFIS-based predictions are slightly superior to the FIS-based predictions. Furthermore, numerical examples manifest that the neuro-fuzzy approach provides superior accuracy in sediment transport modeling without incorporating different multipliers for uprush and backwash.