黄河内蒙古段开河日期预报模型及应用

对黄河内蒙古段的冰情特点进行分析,选用1970—1971年度至2007—2008年度共38个冬季的冰情资料,提取合适的预报因子,分别采用人工神经网络模型和多元线性回归模型,对黄河内蒙古段的开河日期进行预报。结果表明,神经网络模型和多元线性回归模型预报样本合格率分别为86.7%和80.0%,神经网络模型的预报精度高于多元线性回归模型,更适用于黄河内蒙古段开河日期预报。

Application of the break-up date prediction model in the Inner Mongolia Reach of the Yellow River

The ice flood characteristics in Inner Mongolia reach of the Yellow River are analyzed in the papers.Selecting from 1970—1971year to 2007—2008 year ice conditions data and extracting the appropriate predictors,we use artificial neural network model and multiple linear regression model to forecast the date of break-up in Inner Mongolia reach of the Yellow River.The results show that predicition sample pass rates of the artificial neural network model and multiple linear regression model are respectively 86.7%and 80.0%.This indicates that forecasting accuracy of artificial neural network model is better than the one of multiple linear regression model,and the artificial neural network model is applied to the ice forecast of break-up date.