统计相关条件下降水及洪水预报误差相关分析

Correlation Analysis of Precipitation Forecasting Errors and Flood Forecasting Errors Based on Statistical Correlations

以三峡水库上游寸滩至万县区间降水预报误差和入库洪水预报误差相应数据为例,在探讨两者统计相关性的基础上,采用Frank、Gumbel、Clayton三种二元Copula连接函数分析了两预报误差的相关结构,以离差平方和最小为准则进行了Copula函数的选择,并与两预报误差独立情况下联合频率分布进行比较和分析。研究结果表明,降水预报误差和洪水预报误差的相关性对其二元联合分布有一定影响,同时,在两预报误差负相关条件下,其联合分布可做简化处理。本文研究结果可为水库预报调度风险管理提供决策参考。

Taking the precipitation forecasting errors for the reach from Cuntan to Wanxian and inflow flood forecasting errors for Three Gorges Reservoir as an example, the Frank copula, Gumbel copula and Clayton copula were used to analyze the relevance formation of two forecasting errors based on discussing the statistical correlations for the two forecasting errors, and the selection of copula function was performed on the rule of minimum of sum square variation, then the theoretical bivariate joint distribution frequencies were compared to the results of dependent condition. The results demonstrate that considering the correlations between the two forecast errors has some impact on frequency of joint distribution, and on the negative correlation condition, the calculation of the joint distribution between two forecast errors can be simplified. These results may give guidance to the forecasting operation risk management of reservoirs.