Abstract
To improve the overall accuracy of tidal forecasting and ameliorate the low accuracy of single harmonic analysis, this paper proposes a combined tidal forecasting model based on harmonic analysis and autoregressive integrated moving average–support vector regression (ARIMA-SVR). In tidal analysis, the resultant tide can be considered as a superposition of the astronomical tide level and the non-astronomical tidal level, which are affected by the tide-generating force and environmental factors, respectively. The tidal data are de-noised via wavelet analysis, and the astronomical tide level is subsequently calculated via harmonic analysis. The residual sequence generated via harmonic analysis is used as the sample dataset of the non-astronomical tidal level, and the tidal height of the system is calculated by the ARIMA-SVR model. Finally, the tidal values are predicted by linearly summing the calculated results of both systems. The simulation results were validated against the measured tidal data at the tidal station of Bay Waveland Yacht Club, USA. By considering the residual non-astronomical tide level effects (which are ignored in traditional harmonic analysis), the combined model improves the accuracy of tidal prediction. Moreover, the combined model is feasible and efficient.
Highlights
Tide is the periodic rising and falling of the sea level, and its fluctuations largely influence human lifestyle
After hundreds of years of development, harmonic analysis continues to be widely used in tidal prediction; this model only considers the astronomical tidal level affected by the tide-generating forces
The current study proposes a tidal prediction model based on harmonic analysis and an autoregressive integrated moving-average–Support vector machines (SVM) for Regression (ARIMA-support vector regression (SVR)): The model uses the typical time-series-processing model Autoregressive Integrated Moving Average Model (ARIMA) and the SVR, with an excellent nonlinear-data regression performance, to predict the residual sequence generated by the prediction of harmonic analysis
Summary
Tide is the periodic rising and falling of the sea level, and its fluctuations largely influence human lifestyle. After hundreds of years of development, harmonic analysis continues to be widely used in tidal prediction; this model only considers the astronomical tidal level affected by the tide-generating forces. Oliveira et al [14] proposed an evolutionary hybrid system composed of an exponential smoothing filter, the Autoregressive Integrated Moving Average Model (ARIMA), autoregressive (AR) linear models, and an SVR model, which has been proven to have good prospects in the forecasting field Given this diversity of applications, the prospects of SVM in tidal prediction are high. Tidal prediction by SVM has rarely been reported To exploit these prospects, the current study proposes a tidal prediction model based on harmonic analysis and an autoregressive integrated moving-average–SVM for Regression (ARIMA-SVR): The model uses the typical time-series-processing model ARIMA and the SVR, with an excellent nonlinear-data regression performance, to predict the residual sequence generated by the prediction of harmonic analysis. The verification proves that the combined model effectively ameliorates the low accuracy of a single model and provides effective tidal prediction
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call