Radar Data Assimilation of the GRAPES Model and Experimental Results in a Typhoon Case

Constructing βmesoscale weather systems in initial fields remains a challenging problem in a mesoscale numerical weather prediction （NWP） model. Without vertical velocity matching the βmesoscale weather system, convection activities would be suppressed by downdraft and cooling caused by precipitating hydrom eteors. In this study, a method, basing on the threedimensional variational （3DVAR） assimilation technique, was developed to obtain reasonable structures of βmesoscale weather systems by assimilating radar data in a nextgeneration NWP system named GRAPES （the Global and Regional Assimilation and Prediction System） of China. Singlepoint testing indicated that assimilating radial wind significantly improved the horizontal wind but had little effect on the vertical velocity, while assimilating the retrieved vertical velocity （taking Richardson’s equation as the observational operator） can greatly improve the vertical motion. Ex periments on a typhoon show that assimilation of the radial wind data can greatly improve the prediction of the typhoon track, and can ameliorate precipitation to some extent. Assimilating the retrieved vertical velocity and rainwater mixing ratio, and adjusting water vapor and cloud water mixing ratio in the initial fields simultaneously, can significantly improve the tropical cyclone rainfall forecast but has little effect on typhoon path. Joint assimilating these three kinds of radar data gets the best results. Taking into account the scale of different weather systems and representation of observational data, data quality control, error setting of background field and observation data are still requiring further indepth study.