In order to improve the accuracy of tidal level prediction in port and wharf，we propose a self-adapting particle swarm optimization(SAPSO)algorithm to optimize the back propagation(BP)neural network model.The model is referred to as SAPSO-BP model which employs PSO to adjust control parameters of BP network.This novel model overcomes the shortcoming of traditional BP neural network,which is sensitive to the initial weight threshold and is easy to trap in local minimum.The real-measured tidal level data of Isabel port is chosen as the test database to verify the practicability and reliability of the SAPSO-BP prediction model.