摘要
近年来,通过适应性观测技术来减小预报误差已成为国际上数值预报中的一项关键技术,然而实施适应性观测对减小预报误差的影响评估是一个需要深入讨论的问题。文中利用奇异向量方法以2007年3月4日东北地区暴风雪天气过程为研究对象,考察了预报误差对不同观测区域观测资料的敏感性,在确定能量范数的基础上,分析了奇异向量的水平分和特征和垂直分布特征,利用奇异向量的空间结构确定了敏感区域。通过伪逆初始扰动场作为分析误差,研究验证区域的预报误差对不同区域增加观测的敏感性,试验结果表明,在敏感区域内进行补充观测来改善分析误差,能够最有效地提高验证区域内的预报水平;而减小非敏感区域内的分析误差对减小预报误差的贡献相对较小。这些结果表明,利用奇异向量法定义敏感区进行适应性观测,能够和有限的观测资源和计算资源的条件下,最大程度地减小验证区域的预报误差,从而达到提高验证区域预报准确率的目的。
In recent years,the targeting observations techniques are becoming more crucial for improving forecast skill in the numerical weather predicilion.However,how to qualify the effect of applying adaptive observation on forecast errors deserves further discussion.Singular vectors method was used to analyze the sensitivity of forecast error in a blizzard storm event happening in 4 March 2007 which struck the northeastern China severely.Under constraining of energy norm defined by kinetic and potential energy,the singular vectors were calculated and their accuracy was verified,and the three-dimensional structure of singular vectors was studied in detail in this paper.The sensitivity area was defined using the first several singular vectors. The pseudo-inverse initial perturbation was used as an analysis error to test the sensitivity of forecast errors in the verificational region to the observations in the different regions.The results showed that when sampling extra observations in small regions, it was possible to improve the level of forecast only by improving the analysis error in the sensitivity area.Adding observations in the non-sensitivity areas had little impact on the forecast improvement in the validation area.suggesting that taking targeting observations in the sensitivity area defined by singular vectors is able to use finite observations and resources more efficiently for reducing the forecast error,and thus enhancing the accuracy of forecast.
出处
《气象学报》
CAS
CSCD
北大核心
2010年第6期967-976,共10页
Acta Meteorologica Sinica
基金
国家高技术研究发展计划(863计划)(2009AA12Z144)
国家自然科学基金资助项目(41075078
40775067和2007LASW01)
关键词
适应性观测
奇异向量
敏感区域
预报误差
Targeting observations
Singular vectors
Sensitivity area
Forecast error