RIVER ICE CONDITIONS FORECAST BY ARTIFICIAL NEURAL NETWORKS

Ice condition forecasts are very important for preventing ice disasters. Because of the complexity of ice conditions, traditional methods could hardly give accurate prediction in the ice condition forecast, especially for the meandering rivers as the Yellow River, while the artificial neural networks (ANNs) have obvious advantage over other traditional methods for forecasting ice condition. An ANN model based on feed-forward back-propagation (FFBP) and improved by Levenberg-Marquardt algorithm is applied to forecast the ice condition. The study is applied to forecasting ice condition of the Yellow River in the Inner Mongolia Region. The forecast results in the winter of 2004-2005 are in good agreement with the measured ones. Simulation also shows that the ANN model is superior to the MLR model and GM (0,1) model.