多模式融合的广东网格定量降水预报方法的研发与评估  

Development and Verification of a Gridded Quantitative Precipitation Forecast Method in Guangdong Province Based on Multi-Model Integration

作　　者：罗聪[1] 张华龙[1] 曾沁 胡胜[1,3] 吴乃庚[1,3] 陈炳洪[1,4] 时洋 黄晓莹[1] 唐思瑜[1] LUO Cong;ZHANG Hualong;ZENG Qin;HU Sheng;WU Naigeng;CHEN Binghong;SHI Yang;HUANG Xiaoying;TANG Siyu(Guangdong Meteorological Observatory,Guangzhou 510080;National Meteorological Information Centre,Beijing 100081;Institute of Tropical and Marine Meteorology,CMA,Guangzhou 510080;Guangzhou Meteorological Observatory,Guangzhou 511430)

机构地区：[1]广东省气象台,广州510080 [2]国家气象信息中心,北京100081 [3]中国气象局广州热带海洋气象研究所,广州510080 [4]广州市气象台,广州511430

出　　处：《气象》2021年第5期539-549,共11页Meteorological Monthly

基　　金：广东省省级科技计划项目(2019B020208016,2018B020207012);广东省气象局科技项目(GRMC2018Z05)与广东省气象局智能网格预报技术创新团队(GRMCTD202004)共同资助

摘　　要：基于ECMWF全球集合预报、华南区域GRAPES中尺度模式及短时临近预报模式,对不同模式降水预报在广东气候背景下的应用效果进行分析,发展耦合多种方法的客观释用产品,实现多尺度模式的融合应用。通过个例和批量检验,结果表明:多尺度模式融合是一个有发展前景的模式客观释用技术,利用频率匹配和最优百分位方法发挥集合预报解释在天气尺度的应用优势,并基于本地化分型检验建立了强降水空间订正和晴雨消空订正方法,进一步优化了特定天气场景下降水空间分布和强度的预报,利用中尺度模式对日变化特征描述的优势,进行时间降尺度,一定程度上提高了逐时降水预报能力;考虑不同订正方法的相互依赖和影响,确立了“频率匹配-最优百分位-强降水空间订正-晴雨消空订正-时间协调一致”的广东网格定量降水释用流程,实现了多种不同技术的耦合集成,形成优势互补,提升了广东降水客观预报的准确性。This study evaluates the performance of the ECMWF global ensemble prediction system,the short-term-forecast mesoscale model,and the rapid-updated nowcasting model for South China based on GRAPES,by analyzing the spatio-temporal characteristics of precipitation forecast under the local climate background of Guangdong Province.Based on the evaluation results,a hybrid method for multi-model post-processing is developed to produce high-resolution gridded quantitative precipitation forecast(GQPF).The results are as follows:Multi-scale model integration is a promising technique for objective model post-processing.The frequency-matching and optimal-percentile methods show the advantages in ensemble forecast interpretation at synoptic scale,while the spatial correction and clear-rainy elimination based on localized stratified verification can help further optimize the space distribution and intensity for specific weather scenarios.Temporal downscaling based on the characteristics of the mesoscale model in diurnal variation is beneficial to improve the hourly precipitation forecasting.Considering the interdependence and complementary advantages of different methods,the GQPF method for Guangdong is established with a sequential flow of“frequency-matching,optimal-percentile,spatial correction,clear-rainy elimination,time-downscaling”,which improves the accuracy of precipitation objective forecast.

关 键 词：多模式融合 网格定量降水 强降水空间订正 晴雨订正 优选集成 

分 类 号：P456[天文地球—大气科学及气象学]