基于百分位法确定流域极端事件阈值

Determine threshold of basin extreme events based on percentile method analysis

为了解决物理量具有区域性而引起全局分析的不准确性问题,本研究提出一种基于百分位法确定全流域极端事件阈值的新方法。使用该方法对洞庭湖流域的极端降水事件进行分析研究,确定了洞庭湖全流域极端降水阈值,并利用该阈值统计了洞庭湖全流域1961-2009年极端降水频数,对洞庭湖流域极端事件研究具有重要意义。49年来,洞庭湖流域降水频数呈不明显的增加趋势,但1998、1999、2002年极端降水事件发生次数明显增多,而在这几年洞庭湖流域均遭遇了严重的洪涝灾害,这与洞庭湖流域最近几年由于暴雨或大暴雨发生频率增加,导致洞庭湖流域洪涝灾害严重的事实相符。

Thresholds of extreme precipitation events at different gauge stations could be quite different due to regional characteristics and this causes errors in identification of these events over the whole basin. How to determine an extreme threshold for the whole basin is a basic issue. This paper develops an objective identification method for determination of the threshold of extreme precipitation events. This method was applied to the Dongting Lake basin, and a threshold of 22.36 mm was obtained. As a test case, the threshold value was used to find the time trend of extreme precipitation events over the basin in the period of 1961 - 2009. Results show that the threshold provides a good indicator for risk management and detection of local extreme precipitation events.