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 thunderstorm system, emigation rate, liquid water content and cumulative liquid water content. There are significant differences in these features between hail and short time intense precipitation. In addition, these features 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 iterative mechanism is introduced in the classification tree. Experiments show that the recognition rate of systems 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 average critical success index (CSI) reaches 80.0%.