Sequential learning radial basis function network for real-time tidal level predictions

Real time tidal level prediction is essential for management of human activities in coastal and marine areas. However, prediction model with static structure cannot represent the variations caused by time-varying factors such as weather condition and river discharge. This paper presents the application of a sequential learning radial basis function (RBF) network for accurate real-time prediction of tidal level. The proposed prediction model employs a sliding data window as dynamical observer, and tunes the structure and parameters of RBF network to adapt to the dynamical changes of tide. The algorithm uses only short-period data as training data and generates predictions sequentially. Hourly tidal data measured at seven tidal stations on west coast of Canada are used to test the effectiveness of the sequential prediction model. Tidal level prediction performance shows that the proposed model can give accurate short-term prediction of tidal levels with very low computational cost.

► A variable structure RBF network is adopted for real-time tidal level prediction.
► The structure and connecting parameters of the network are real-time adjusted.
► The samples are learned in a sliding data window sequentially.
► The network achieves satisfactory short-term tidal level prediction performance.
► The prediction model is featured by high accuracy and low computational costs.