MIGFA阵风锋识别算法改进与检验

Improvement of the MIGFA Technique for Identifying Gust Front and Its Verification

根据南京CINRAD/SA天气雷达探测的江苏沿江地区阵风锋回波特征,对MIGFA(Machine Intelligence Gust Front Algorithm)阵风锋识别算法进行改进:在考虑平滑算法使用和低仰角数据融合的基础上,根据阵风锋回波特征,改进了0.5°反射率阵风锋细线函数模板,设计了较高仰角(1.5°/2.4°)反射率阵风锋细线函数模板,引入1.5°和2.4°双层反射率阵风锋细线函数模板替代原空间差分反射率函数模板。考虑阵风锋特征与距离测站的关系,设计了动态权重函数组合多组得分值,从而有效识别阵风锋回波。在此基础上通过弧度判断和阵风锋回波平坦度测试的方式,进一步降低虚警率。最后利用2009年6月14日南京雷达阵风锋个例进行效果识别,并采用临界成功指数对南京雷达120个阵风锋样本进行效果评估。结果表明:改进的MIGFA法识别效果良好,将临界成功指数从0.39提高至0.60,引入降低虚警率的做法使得虚假警报率从0.34降至0.16。

The improvement of the MIGFA technique is made based on the gust front echo features along the Yangtze River in Jiangsu detected by the Nanjing CINRAD/SA weather radar. Considering the smoothing algorithm and the low elevation data fusion, the 0.5° reflectivity echo thin line functional template is improved and the higher elevation echo thin line functional template is designed based on the gust front fea- tures. The original spatial difference reflectivity functional template is replaced by the double higher elevation reflectivity thin line functional templates. A group of the dynamic-weighting functions is designed to combine the score array by the relationship of the gust front features and its distance from the station so as to effectively identify the gust front echo. Through the angle judgment and the echo flatness testing, the false alarm rate is further reduced. Finally, the effect of the identification is made by the gust front process seen on 14 June 2009 and detected with the Nanjing radar. And the effect of the evaluation is also made by 120 gust front samples in Nanjing radar. The results show that the critical success index is increased from 0.39 to 0.60 and the false alarm rate is reduced from 0.34 to 0.16 through the improving MIGFA.