台风预报误差的流依赖特征及混合资料同化中最优耦合系数

Flow-dependent characteristics of typhoon forecasting errors and optimal coupling coefficient in hybrid data assimilation

基于集合卡尔曼变换与三维变分(ETKF-3DVAR)混合资料同化系统和欧洲中期天气预报中心(ECWMF)的全球集合预报,以"梅花"台风为例,分析了台风系统预报误差的流依赖特征,讨论了耦合系数在混合同化和预报中的敏感性及其对预报质量的影响。结果显示,台风系统的预报误差协方差具有显著的中小尺度结构特征,集合估计的预报误差协方差结构能够再现其流依赖属性。相对于3DVAR方案,混合资料同化方案的最优耦合系数对台风系统的分析和预报质量具有更好的改善;但不同的耦合系数对台风路径预报有明显的影响,不合适的耦合系数甚至可能导致更坏的结果,只有耦合了相对合适的预报误差协方差的流依赖信息,混合资料同化方案才可能对分析和预报质量有正效果。这表明在混合资料同化系统中,构造一种具有自适应能力的耦合权重函数,实现相对最优权重的自动选择,对充分发挥混合资料同化方案的潜在优势具有重要意义。

Based on the WRF ETKF-3DVAR hybrid data assimilation system and 51 members of ECWMF global ensemble prediction in TIGGE data,the flow-dependent characteristics of typhoon forecasting errors,the sensitivity of coupling coefficient in hybrid data assimilation and forecast,and its effects on forecast skill are analyzed,taking typhoon Muifa for example. Results suggest that the forecasting error covariance of typhoon has significant meso-and small-scale characteristics and the structure of forecasting error covariance that is estimated according to ensemble prediction can reappear its flow-dependent nature. The optimal coupling coefficient in hybrid data assimilation scheme can better improve the qualities of analysis and forecast of typhoon than 3 DVAR scheme. However,there are obvious effects on typhoon track forecast for different coupling coefficients and an improper coupling coefficient can lead to a worse result. That is,only the relative appropriate flow-dependent information in forecasting error covariance is coupled,the hybrid data assimilation scheme can have positive effects on the qualities of analysis and forecast. It shows that,in the hybrid data assimilation system,constructing a coupling weight functionwith adaptive ability and achieving automatically the aim to choose optimal coupling coefficient are of importance to improve forecast quality and give full play to potential advantage of hybrid data assimilation system.