Back-propagation neural network for long-term tidal predictions

Abstract

During the recent years, the availability of accurate ocean tide models has become increasingly important, as tides are the main contributor to disposal and movement of sediments, tracers and pollutants, and to a whole range of offshore applications in engineering, environmental observations, exploration and oceanography. Tides can be conventionally predicted by harmonic analysis, which is the superposition of many sinusoidal constituents with amplitudes and frequencies determined by a local analysis of the measured tide. However, accurate predictions of tide levels could not be obtained without a large number of tide measurements by the harmonic method. An application of the back-propagation neural network using short-term measuring data is presented in this paper. On site tidal level data at Taichung Harbor in Taiwan will be used to test the performance of the present model. Comparisons with conventional harmonic methods indicate that the back-propagation neural network mode also efficiently predicts the long-term tidal levels.