Application of artificial neural network to calculation of solitary wave run-up

The prediction of solitary wave run-ups has important practical significance in coastal and ocean engineering. But the precision of calculating is limited from the existing models. Artificial neural network technology has rapidly developed and been widely used in many fields. In this paper, a solitary wave run-up calculation model is established based on artificial neural networks. A BP network with one hidden layer is modified by an additional momentum method and an auto-adjusting learning rate. The correlation coefficients between the model results and the experimental values are 0.9635 and 0.9965, respectively. It is concluded that the neural network model is an appropriate methodology to be applied to solitary wave run-up scenario calculation and analysis.