基于PDS/GP模型分析汉江流域降雨极值特征

Analysis of Rainfall Extreme in Han River Basin Based on PDS/GP Model

以汉江流域15个气象站1961~2010年的实测逐月降雨系列为例,将平均超出量函数和参数估计量变化两种阈值选取方法相结合,确定了各系列的合理阈值,并采用拟合残差法来减小阈值选取的不确定性。采用超定量（PDS）和年最大（AM）取样方法,选择广义Pareto（GP）和皮三型（PIII）分布,分别构建PDS/GP和AM/PIII模型,分析汉江流域降雨极值变化特征,预测汉江流域各站20年、50年、100年和200年一遇的月降雨极值。对比分析两种模型的计算结果,AM/PIII模型的估计值普遍大于PDS/GP模型,但受月降雨极值年际变化和空间差异的影响,差别不显著。

The monthly rainfall of 15 meteorological stations in Han River basin from 1961 to 2010 was taken as case study. Two methods of mean residual life and change of parameters were combined to determine the proper thresholds for each data series, and the fit residuals method was adopted to reduce the uncertainty during the process. Partial duration series （PDS） and annual maximum （AM} series were obtained and fitted by General Pareto （GP） and Pearson Type Ⅲ （PⅢ） distributions, respectively. The PDS/GP and AM/PⅢ models were constructed and used to analyze rainfall extreme variations and predict rainfall quantiles with 20a, 50a, 100a and 200a return periods for each station. The results and comparison indicated that the estimates supplied by AM/PIll model were mostly lager than that of PDS/GP model, while the differences were not so much significant because of the temporal and spatial variations of the monthly rainfall extremes.