عنوان مقاله [English]
Prediction of waves in coastal engineering and marine issues is essential.
For this purpose, various methods including experimental methods, numerical methods and computational software tools exist.
Experimental methods are relatively simple, but in comparison with other methods are not accurate.
Numerical models are generally accurate, but use them time and money wants.
In recent decades, the use of artificial neural networks have been widely applied to solve many engineering problems of the sea. It is capable in the modeling nonlinear problems.
This paper conducted in Bandar Anzali, Caspian predicting in the wave height of the artificial neural network technique is used. Data obtained from the Ports and Shipping Organization and the Caspian Oil Company, in the periods 3,6, 12 and 24 h were measured by ADCP system.
Network using Feed-forward three-layered networks with four neurons in the middle layer, which produces the best prediction.