高时空分辨率三维风场在强对流天气临近预报中的融合应用研究

Fusion of 3D high temporal and spatial resolution wind field and its application in nowcasting of severe convective weather

以业务应用为目标,开展高时、空分辨率三维风场在强对流天气临近预报中的融合应用研究。运用北京快速更新多尺度分析和预报系统集成子系统(RMAPS-IN,Rapid-refresh Multi-scale Analysis and Prediction System-Integration),对雷达四维变分分析系统(VDRAS)30 min临近预报的高时、空分辨率三维风场作为数据源与自动气象站风场观测进行快速融合处理。结果表明,以VDRAS临近预报风场取代数值模式预报场作为融合初猜场后形成的分析结果对于风场有明显的改善:(1)长时间序列客观检验结果表明,地面10 m高风场U/V分量绝对误差分别为0.05和0.06 m/s。实时融合对未来预报的影响随着预报时效的延长,U/V分量的绝对误差不断增大。(2)对于11个强对流个例,地面10 m高风场风速均方根误差降低0.3 m/s,风向均方根误差降低13°;边界层三维风场,风速均方根误差降低0.8 m/s,风向均方根误差降低10°。平原站点融合以后风速、风向预报效果有较大改善,山区站点融合以后改善相对较小。(3)通过对2017年7月20日暴雨和7月7日雷暴大风个例的详细分析,发现融合基于雷达资料四维变分同化获得的高分辨率临近预报风场对各对流系统中的中尺度结构特征给出了更加细致准确的描述。

The Rapid-refresh Multi-scale Analysis and Prediction System-Integration(RMAPS-IN) is used in this study to merge the nowcasting three dimensional high spatial and temporal resolution wind field from Variational Doppler Radar Analysis System(VDRAS) with the wind field observed at automatic stations. The results show that the analysis results can obviously improve the wind field.(1)The long time series objective test results show that the absolute errors of U/V components are 0.05 and 0.06 m/s, respectively;the absolute errors of U/V components increase with the forecast lead time for the 10 m ground wind field.(2)For the cases of strong convection, the root mean square errors of the 10 m ground wind speed and wind direction are respectively reduced by 0.3 m/s and 13°, and the root mean square errors of wind speed and wind direction are respectively reduced by 0.8 m/s and 10° for the 3-D high resolution wind field. The wind speed and wind direction have been greatly improved in plain sites and the improvements are relatively small in mountain sites.(3)A detailed analysis of the rainstorm occurred on 20 July 2017 and the thunderstorm gale occurred on 7 July 2017 is given. The results show that the RMAPS-IN wind field fusion products can provide more detailed and quantitative description of meso-scale systems.