高密度雷达网风场反演的优化方法及其应用效果检验

The optimization method for wind field retrieval using high-density radar networks and its application effect verification

高质量多普勒天气雷达三维风场反演产品是研究和预报中小尺度天气系统不可或缺的资料。现有的天气雷达三维变分风场反演方法(3DVAR)主要基于单部或数部雷达进行小范围风场反演,利用多部雷达资料进行而大范围风场反演计算量大、程序运行速度慢,不利于业务有效开展。利用广东省11部S波段多普勒天气雷达和27部X波段相控阵天气雷达,在3DVAR方法的基础上,结合双雷达风场反演方法提出了一种能够获得高质量大范围风场结果的优化方法(D-3DVAR)。优化过程共分三步:①基于天气系统位置确定风场反演区域从而减少雷达数量;②通过计算雷达网在双雷达风场反演贡献比例减少雷达数量;③在双雷达风场反演过程中每个格点仅选取最优的两个径向速度进行风场反演计算,其余径向速度不参与后续的风场反演,每进行一步优化后进行风场反演的结果记为优化1—3。以2022年5月13日广东沿海地区一次飑线过程为例,应用D-3DVAR方法对雷达网风场进行反演,并对反演结果进行对比检验。结果表明,三步优化的风场反演方法能够得到大湾区大范围的双多普勒雷达风场反演结果,在2km高度能够较好覆盖大湾区陆地区域,在4km高度能够覆盖海岸线内大部分区域。相较优化1,优化2和优化3的风场反演程序运行速度提高了3倍,优化3与优化1的风场反演结果基本特征一致,风速误差基本小于1.7m·s^(-1),风向误差基本小于10°;但优化3的风场反演结果更能突出中小尺度天气系统风场强上升气流和垂直涡旋特征。

High-quality three-dimensional wind field retrieval products from Doppler weather radars are essential data for studying and forecasting mesoscale weather systems.The existing 3D variational wind field retrieval method(3DVAR)mainly uses data from single or multiple radars to conduct the wind field retrieval of small regions.However,for wind field retrieval of large regions using multiple radars,challenges exist,such as high computational requirements and slow processing speeds,which obstruct operational applications.In this study,anan improved method(D-3DVAR)that can obtain high-quality large-scale wind field results is proposed by combining the dual-radar wind field retrieval method,based on the 3DVAR method,using 11 S-band Doppler weather radars and 27 X-band phased array weather radars in Guangdong Province.The optimization process consists of three steps.First,determine the wind field retrieval area based on the location of the weather system to reduce the number of radars;Second,reduce the number of radars by calculating the contribution ratio of the radar network in the dual-radar wind field retrieval;Third,during the dual-radar wind field retrieval process,only select the optimal two radial velocities for each grid point to conduct the wind field retrieval,while the remaining radial velocities do not participate in subsequent wind field retrieval.The results of wind field retrieval after each optimization step are recorded as Majorization 1-3.Taking a squall line process along the coastal area of Guangdong Province on 13 May 2022,as an example,wind field retrieval was performed on the radar network using D-3DVAR,and the retrieval results were compared and verified.The results show that the three-step optimized wind field retrieval method can obtain dual-Doppler radar wind field retrieval results for a large area of the Greater Bay Area,which can better cover the land area of the Greater Bay Area at an altitude of 2 km and most areas within the coastline at an altitude of 4 km.Compared to Majorization 1,the wind field retrieval program execution speed of Majorization 2 and 3 is increased by 3 times.The basic characteristics of Majorization 3 and Majorization 1 are consistent,with wind speed errors less than 1.7 m·s^(-1) and wind direction errors within 10°.However,the wind field retrieval result of Majorization 3 can better highlight the characteristics of strong updraft and vertical vortex in the wind field of mesoscale weather systems.