An adaptive real-time modular tidal level prediction mechanism based on EMD and Lipschitz quotients method

Abstract

Real-time prediction of tidal level is vital for on-the-spot activities such as marine transportation and ocean surveys. Aiming at the complex characteristics of nonlinearity, time-varying dynamics, and uncertainty generated by celestial bodies' movements and influenced by geographical as well as hydrometeorological factors, an adaptive real-time modular tidal level prediction mechanism is proposed based on empirical mode decomposition (EMD) and Lipschitz quotients method. An adaptive modular tidal level prediction mechanism is proposed by combining the harmonic analysis method with a variable structure neural network. The order of time series decomposition and the prediction input model order of the neural network are automatically determined based on EMD and the Lipschitz quotients method, respectively. The adaptability of the prediction mechanism is further enhanced with the network dimension, hidden units’ locations, and connecting parameters of the variable neural network being online adjusted in a sequential learning scheme. While the extraction of harmonic components alleviates the difficulty in prediction, the multi-resolution decomposition of residual series provides further insight into the time-varying tide dynamics caused by environmental disturbances, thus enabling precise predictions for tidal levels. The feasibility and effectiveness of the proposed adaptive modular tidal prediction mechanism are demonstrated based on the real-measured tidal level data.