Calculation of Tongguan Elevation in flood seasons by the improved BP neural network with GA

The ANN(Artificial Neural Networks) has the merit in searching the better from the part in the whole,and the GA(Genetic Algorithm) has the merit in searching the better from the whole.In this paper the merits of these two methods have been combined and a new BP neural networks model is developed.Comparing with the normal BP neural network,the new model efficiently improves the accuracy and convergent speed.The application shows that the proposed model can reasonably simulate the change of Tongguan Elevation under various conditions.It is expected that the proposed model could be used to solve such nonlinear problems in other similar cases.