No abstract

No abstract

Forecasting of wave parameters is necessary for many marine and coastal operations.Different forecasting methodologies have been developed using the wind and wave characteristics. In this paper, Artificial Neural Network (ANN) as a robust data learning method is used to forecast the wave height for the next 3, 6, 12 and 24 hours in the Persian Gulf. To determine the effective parameters, different models with various combinations of input parameters were considered. Parameters such as wind speed, direction and wave height of the previous three hours, were found to be the best inputs. Furthermore, using the difference between wave and wind directions showed better performance. The results also indicated that if only the wind parameters are used as model inputs the accuracy of the forecasting increases as the time horizon increases up to 6 hours. This can be due to the lower influence of previous wave heights on larger lead time forecasting and the existing lag between the wind and wave growth. It was also found that in short lead times, the forecasted wave heights primarily depend on the previous wave heights, while in larger lead times there is a greater dependence on previous wind speeds.

Scour around submarine pipelines remains a largely complex and not yet fully understood problem. In this study, wave-induced scour around submarine pipelines was investigated. Since various physical processes occur during the development of a scour hole, the effects of each process were considered by employing several nondimensional parameters. To find the effective parameters on equilibrium scour depth, the correlation between independent parameters (e.g. Keulegan-Carpenter number) and dependent parameter (nondimensional scour depth) were determined using different experimental data. Then, an Artificial Neural Network (ANNs) approach was used to develop a more accurate model for prediction of wave-induced scour depth around submarine pipelines. ANN models with different input parameters including gap to diameter ratio, Keulegan-Carpenter number, pipe Reynolds number, Shields number, sediment Reynolds number and boundary layer Reynolds number were trained and evaluated to find the best predictor model. To develop the ANN models, both holdout and tenfold cross-validation methods were used. In addition, an existing empirical method was examined. Results show that the empirical method has a significant error in the prediction of scour depth for the cases with an initial gap between pipe and seabed. It is also indicated that the ANN models outperform the empirical method in terms of prediction capability.

No abstract