利用贝叶斯方法对广东省雷暴大风天气的预报研究  

RESEARCH ON THUNDERSTORM GALE WEATHER FORECAST IN GUANGDONG PROVINCE BY USING BAYESIAN METHOD

作　　者：朱泳桦 王咏青[1] 胡志群[2] ZHU Yonghua;WANG Yongqing;HU Zhiqun(Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/Key Laboratory of Meteorological Disasters,Ministry of Education/School of Atmospheric Sciences,Nanjing University of Information Science&Technology,Nanjing 210044,China;State Key Laboratory of Severe Weather,Chinese Academy of Meteorological Sciences,Beijing 100081,China)

机构地区：[1]南京信息工程大学气象灾害预报预警与评估协同创新中心/气象灾害教育部重点实验室/大气科学学院,江苏南京210044 [2]中国气象科学研究院灾害天气国家重点实验室,北京100081

出　　处：《热带气象学报》2023年第6期929-939,共11页Journal of Tropical Meteorology

基　　金：广东省重点领域研发计划(2020B1111200001);国家自然科学基金(41875070、41575040);北极阁开放研究基金(NJCAR2018MS02);云南省科技项目(2018BC007)共同资助。

摘　　要：针对广东省2010—2019年4—9月有雷暴大风和没有雷暴大风天气的个例进行研究,通过箱线图的形式分析了产生雷暴大风天气相关环境参数的分布特征并建立3小时、6小时和12小时三个时间段的雷暴大风潜势预报模型,利用贝叶斯方法对2020年4—9月的天气过程进行检验,结果表明:雷暴大风天气的发生对应地面较高的露点温度,较大的不稳定能量、上下层温差以及全总指数等物理量;从检验结果来看,贝叶斯方法对雷暴大风天气的识别具有一定的可行性,三个时段的潜势预报模型识别雷暴大风的命中率均在80%以上,但存在一定的空报,需今后改进与完善。This paper studied the individual cases of weather with and without thunderstorm gales in Guangdong Province from April to September 2010—2019.The distribution characteristics of environmental parameters related to the weather with thunderstorm gales were analyzed by using boxplots,and the three hours,six hours,and 12 hours thunderstorm gale forecast models were established.The meteorological events from April to September 2020 were tested by using the Bayesian method.The results show that the occurrence of thunderstorm gales corresponds to higher dewpoint temperature on the ground,more unstable energy,temperature difference between upper and lower layers,and total index.According to the test results,the Bayesian method may to some extent identify thunderstorm gales.The hit rate of the prediction model is above 80%,but there are some empty reports,which need to be addressed in the future.

关 键 词：雷暴大风 环境参数 贝叶斯方法 TS评分 潜势预报 

分 类 号：P456[天文地球—大气科学及气象学]