汉江流域极端水文事件时空分布特征

Spatiotemporal Distribution Features of Extreme Hydrological Events in the Hanjiang River Basin

利用1960—2012年汉江流域15个气象站点的日降雨资料和3个水文站同时期日径流资料,分析了9个极端降雨指数的空间分布规律,运用广义极值分布(GEV)、Gamma分布两种极值统计模型对各站点的最大1 d降雨、最大3 d降雨极值样本进行拟合,遴选描述降雨极值分布规律最优概率模型,进而推算给定重现期下的降雨设计值,并分析其空间分布规律;选用Gumbel、Clayton和Frank这3种Copula函数建立降雨-洪量极值联合分布模型,优选最合适的Copula函数,由此计算给定重现期下的洪量设计值。结果表明:GEV分布模型能更好地模拟降雨极值序列,不同重现期下的降雨极值在空间上均呈西低东高的特征;3种Copula函数中,Frank Copula函数能更好地拟合降雨-洪量相关关系,由此推求的洪量设计值大于单变量拟合设计值。

The spatial distribution rules of 9 extreme precipitation indices are analyzed based on the daily precipitation data from 15 meteorological stations and the daily runoff data from 3 hydrological stations in the Hanjiang River basin from 1960 to 2012. The generalized extreme value（GEV） model and the Gamma model are selected for the fitting of each station？s extremum samples of maximum 1-day precipitation and maximum 3-day precipitation to single out the best statistical model, and then the precipitation design value with the given recurrence interval is calculated and its spatial distribution rules are analyzed. A joint distribution model of precipitation and flood volume is built based on three Copula functions including the Gumbel, the Clayton and the Frank, and the most appropriate Copula function model is chosen to calculate the design value of the flood volume with the given recurrence interval.The result shows that the GEV model can better simulate the extreme precipitation sequence, and the extreme precipitation in the recurrence interval presents a feature that it is high in the east and low in the west. In comparison with other Copula functions, the Frank Copula function is better to simulate the correlation relationship between the precipitation and the flood volume, and the design value of the flood volume obtained by this function is greater than the design value derived from the fitting of univariate distribution.