Yuan, H.; Tan, M., and Wang, W., 2015. Selection of methods for predicting tidal levels with a typhoon surge effect.
Accurate prediction of tidal level with strong meteorological effects is very important for human activities in oceanic and coastal areas. Under severe weather, such as typhoons, the contribution of non-astronomical components to tidal level may be as significant as that of astronomical components. The traditional harmonic analysis method and other models based on the analysis of astronomical components do not work well in these situations. The objective of this paper is to select an effective method for predicting the tidal level under the influence of typhoons at Luchaogang, China. The linear regression, back-propagation (BP) and radial basis function neural network methods are compared. Based on the typhoon data and tidal-level data gathered from Pudong Hydrological Bureau, seven parameters of typhoon are extracted and employed as input parameters while the corresponding tidal-level data are adopted as output parameters. The results have shown that the BP method performs best in the prediction of tidal level with a typhoon effect, and that the BP neural network method can provide a solid basis for tidal-level prediction and typhoon disaster reduction.