经验正交函数方法和TRMM数据对长江流域降水模式与极端水文过程的研究

EMPIRICAL ORTHOGONAL FUNCTION(EOF) AND ITS APPLICATION IN PRECIPITATION PATTERNS RECOGNITION AND HYDROLOGICAL EXTREME STUDIES USING TRMM DATA IN THE YANGTZE RIVER BASIN

气候变化加剧了极端天气和水文事件的发生,降水是区域干旱与洪水事件最直接驱动因素。以TRMM/PR月累积降水反演遥感数据为基础,利用经验正交函数EOF(Empirical Orthogonal Function)方法对长江流域降水时空变化模式进行提取,并对比分析了主要模式振幅强弱与极端水文事件的对应关系。结果表明在流域尺度上EOF方法及TRMM/PR数据可以较好地识别降水主要模式,通过时空尺度变换成功揭示主要降水模式强弱与流域极端水文事件的对应关系。鉴于日益丰富的巨量水文气象时空数据,EOF方法在模式提取、水文模拟、极端事件预估及灾害适应性研究等方面具有应用潜力。

Study indicates the global warming will lead to more extreme events.Dynamics of precipitation patterns are major causes for hydrological disaster.With the aid of EOF method,the precipitation patterns were extracted in the Yangtze River Basin using satellite-derived TRMM/PR monthly accumulated data.Research findings indicate that signals of large-scale precipitation variations can be well identified,and the oscillations in relation to the major PCs are well consistent with the typical hydrological extremes.The EOF analyses constitute a fundamental tool to help explore the inherent patterns existed in spatial databases（satellite image sequences） that explain the primary variability through the decomposition of a space-time field.The retrieved patterns are valuable avenues to help project extreme events,forecast runoff extremes and aid in disaster mitigation in environmental decision-making.