气象Issue(2)：230-237,8.DOI:10.7519/j.issn.1000-0526.2016.02.011
50 km 以内雷暴系统的分类识别方法研究
Method Study of Classification and Recognition of Thunderstorm System Less than 50 km
摘要
Abstract
To solve the problem of automatic classification and recognition of thunderstorm system with horizontal scale less than 50 km,four features are constructed,including the density feature of thunder-storm system,emigation rate,liquid water content and cumulative liquid water content.There are signifi-cant differences in these features between hail and short-time intense precipitation.In addition,these fea-tures can be used to describe complex system that generates hail and short-time heavy precipitation at the same time.In view of the relationship between cumulative liquid water content and time series,the itera-tive mechanism is introduced in the classification tree.Experiments show that the recognition rate of sys-tems generating short-time heavy precipitation is as high as 89.1% and the false positive rate is 9.5%, while the recognition rate of systems generating hail is 79.8% and the false positive rate is 3.5%.The av-erage critical success index (CSI)reaches 80.0%.关键词
50km 以内雷暴系统/结构疏密性特征/移出率/液态水含量/决策树Key words
thunderstorm system less than 50 km/density feature/emigation rate/liquid water content/classification tree分类
天文与地球科学引用本文复制引用
王萍,高毅,李聪..50 km 以内雷暴系统的分类识别方法研究[J].气象,2016,(2):230-237,8.基金项目
天津市科学基金项目（14JCYBJC21800）资助 （）
