Search

A fuzzy inference system (FIS) and a hybrid adaptive network-based fuzzy inference system (ANFIS), which combines a fuzzy inference system and a neural network, are used to predict and model longshore sediment transport (LST). The measurement data (field and experimental data) obtained from Kamphuis [1] and Smith et al. [2] were used to develop the model. The FIS and ANFIS models employ five inputs (breaking wave height, breaking wave angle, slope at the breaking point, peak wave period and median grain size) and one output (longshore sediment transport rate). The criteria used to measure the performances of the models include the bias, the root mean square error, the scatter index and the coefficients of determination and correlation. The results indicate that the ANFIS model is superior to the FIS model for predicting LST rates. To verify the ANFIS model, the model was applied to the Karaburun coastal region, which is located along the southwestern coast of the Black Sea. The LST rates obtained from the ANFIS model were compared with the field measurements, the CERC [3] formula, the Kamphuis [1] formula and the numerical model (LITPACK). The percentages of error between the measured rates and the calculated LST rates based on the ANFIS method, the CERC formula ( K sig = 0.39), the calibrated CERC formula ( K sig = 0.08), the Kamphuis [1] formula and the numerical model (LITPACK) are 6.5%, 413.9%, 6.9%, 15.3% and 18.1%, respectively. The comparison of the results suggests that the ANFIS model is superior to the FIS model for predicting LST rates and performs significantly better than the tested empirical formulas and the numerical model. [ABSTRACT FROM AUTHOR]

This work suggests an alternative approach, namely, the use of an artificial neural network (ANN), for the estimation of longshore sediment transport (LST). The ANN technique provides a powerful utility for input-output mapping if there is sufficient data and can be useful for modeling processes about which adequate knowledge of physics is limited, such as sediment transport. A feed-forward network was developed to predict the LST from a variety of causative variables. The best network was selected after testing many alternatives. The network was validated by experimental and field data. In addition, the ANN method was applied to the case study area (Karaburun, Turkey), located on the SW coast of the Black Sea. The accuracy of the ANN predictions was evaluated against the measured LST rate at Karaburun and compared with two well-known empirical formulas (CERC formula, Kamphuis formula), and a numerical model (LITPACK). The average, net, annual LST rate for the study area was determined based on the morphological volume differences between the surveys. The volume differences were obtained from the accretion at the secondary breakwater of the harbor located at the western end of the 4-km sandy beach. The harbor acted as a total trap, and the beach surveys were extended to an adequate depth. The measured net LST rate was 72,000 m³/y, and the calculated rates were 370,000, 77,000, 83,000, 85,000, and 80,000 m³/y based on the CERC formula (Ksig = 0.39), the modified CERC formula (Ksig = 0.08), the Kamphuis formula, the LITPACK computer program, and the ANN. All methods employed in this study estimated the LST rates well, except the CERC formula. The CERC formula overestimated the LST rate by a factor of five; nevertheless, with the adjustment of the empirical Ksig value (0.39) to 0.08, the fit to the observed data improved significantly. The Kamphuis formula produced results similar to those predicted by the field data. This confirms the use of the Kamphuis formula in conditions of low-wave energy with breaker heights of less than 1 m, which correspond to the study area's wave condition. [ABSTRACT FROM AUTHOR]