A hybrid real-time tidal prediction mechanism based on harmonic method and variable structure neural network. (May 2015)

• Record Type: Journal Article
• Authors: Yin, Jian-Chuan; Wang, Ni-Ni; Hu, Jiang-Qiang
• Is Part Of: Engineering applications of artificial intelligence. Volume 41(2015:May)
• Page Start: 223
• Page End: 231
• Publication Date: 2015-05
• Subjects: Tidal prediction -- Hybrid model -- Variable neural network -- Harmonic method -- Sliding data window; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2015.03.002
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Accurate real time tidal prediction is essential for human activities in coastal and marine fields. Tidal changes are influenced not only by periodic revolutions of celestial bodies but also by time-varying meteorological factors. For accurate real-time tidal prediction, a hybrid prediction mechanism is constructed by taking both advantages of harmonic analysis and neural network. In the proposed mechanism, conventional harmonic analysis is employed for representing the influences of celestial factors; and neural network is used for representing the nonlinear influences of meteorological factors. Furthermore, to represent time-varying tidal dynamics influenced by meteorological factors, a variable neural network is real-time constructed with the neurons and the connecting parameters are adaptively adjusted based on a sliding data window (SDW). The hybrid prediction method uses only the latest short-period data to generate predictions sequentially. Hourly tidal data measured at four American tidal stations are used to validate the effectiveness of the hybrid sequential tidal prediction model. Simulation results of tidal prediction demonstrate that the proposed model can generate accurate short-term prediction of tidal levels at very low computational cost. Highlights: A hybrid tidal prediction mechanism is established based on harmonic method and variable radial basis function network. Influences of time-varying meteorological and other unmodeled factors are represented by variable structure neural network. The proposed hybrid tidal level prediction model achieves satisfactory short-term prediction performance. The hybrid model takes both advantages of first principle knowledge and data-driven variable neural network.