A Modular Tide Level Prediction Method Based on a NARX Neural Network

Tide variations are affected not only by periodic movement of celestial bodies but also time-varying interference from the external environment. To improve accuracy tide prediction, a modular level prediction model (HA-NARX) is proposed. This divides data into two parts: astronomical tide-generating forces and nonastronomical various environmental factors. Final results obtained using nonlinear autoregressive exogenous (NARX) neural network combined with harmonic analysis (HA) data. verify feasibility model, under different climatic geographical conditions used to simulate levels, compared those traditional HA, genetic algorithm-back propagation (GA-BP) wavelet (WNN). The show that greater influence meteorological factors on tides, more obvious improvement in stability HA-NARX models, highest 234%. proposed has simple structure can effectively prediction.