Study On tide prediction method based On LS-Support Vector Machines

The paper analyses the limited of tide prediction based on harmonic analysis method and BP neural network method. According to celestial motion law and weather or other non-periodic factors effect, the author designs a tide prediction method based on Least Square-Support Vector Machines (LS-SVM). This method preferably carries out the tide prediction which influenced by non-cyclical factors. Compared with harmonic analysis method and BP neural network method, this prediction method has faster modeling speed, higher prediction precision and stronger generalization ability.