Study on Prediction of Tide and Ocean Current by Data-Driven Model

Abstract

Tide and ocean current are the major dynamic factors for ocean engineering. The insufficiency of tidal level and ocean current data near the ocean engineering waters may bring uncertainty for ocean engineering design and numerical model. A data-driven model is presented to solve this problem based on Artificial Neural Network (ANN), one site and multi-sites data-driven models are established. Field data under complex geography and hydrodynamic condition are used to validate the performance of the present data-driven models, the nonlinear mapping relation among tidal level and ocean current is reproduced by these models. Comparisons and errors analysis between the numerical results and field-data are satisfactory, which shows the simple structure and good precision of the present models. Furthermore, the data-driven model can be widely useful for solving this ocean engineering problem.