摘要
对国际上现有各种冰坝预测模型进行分析比较,并讨论了各自的优缺点。认为现有的大多数模型是针对某一特定河段建立的,没有一种模型具有明显优势;各种模型的预测结果均具有较大取伪误差,模型中参数选择具有任意性。提出了进一步的研究方向:为了减小预测误差,应增加模型中的变量,并采用统计方法如逐步回归法确定模型变量;为了评价预报结果的可靠性,应对预测误差(包括取伪误差和弃真误差)进行定量分析;对冰坝形成及溃决的机理应进行深入研究。
The existing breakup ice-jam prediction methods and their potential advantages and disadvantages were briefly reviewed. It is pointed out that most of the models used were developed for specific river reaches, none of them showing evident advantages, and that the predicted results by each model are of high false-positive error induced by arbitrary selection of model variables. Thus, it is suggested that statistics methods, such as stepwise regression, should be adopted to determine the model variables and more variables should be included so as to decrease the prediction error, and that the prediction errors, including the false-positive error and false-negative error, should be quantitatively analyzed for evaluation of the reliability of the predicted results. Moreover, the mechanism of ice-jam formation and breakup should be emphasized in further study.
出处
《水利水电科技进展》
CSCD
北大核心
2007年第3期76-80,94,共6页
Advances in Science and Technology of Water Resources
基金
国家自然科学基金(50579030)
关键词
河冰水力学
开河冰坝
冰坝预测
预测模型
综述
river-ice hydraulics
breakup ice-jam
ice-jam prediction
prediction model
review