Levenberg-Marquardt Algorithm Applied to Forecast the Ice Conditions in Ningmeng Reach of the Yellow River

摘要

The characters of Ningmeng Reach of the Yellow River are introduced firstly, followed by the fundamental of neural network and its application. Then the main factors which affect the ice conditions in Ningmeng Reach are analyzed. Furthermore, the BP model based on feed-forward back-propagation and improved by the Levenberg-Marquardt algorithm is set up and applied to forecast the ice conditions in Ningmeng Reach. The forecast results in the winter of 2004ȁ3;2005 are in good agreement with the measured data.