多积云参数化方案热带气旋路径集合预报试验

ENSEMBLE PREDICTION EXPERIMENTS OF TRACKS OF TROPICAL CYCLONES BY USING MULTIPLE CUMULUS PARAMETERIZATION SCHEMES

利用MM5模式采用5种积云参数化方案选项研究了2004～2006年共8个热带气旋路径的集合预报。结果表明，热带气旋路径预报对积云参数化方案的选取是敏感的，积云参数化方案之间优劣互补，而选择无积云参数化方案选项对热带气旋路径的预报有积极的贡献。采用3种路径集合预报方案研究的结果表明，集合方法对热带气旋路径预报有明显的改善，其中无积云参数化Grell、Betts—Miller和Kain—Fritsch4种积云参数化方案选项组合的集合预报效果最好，平均路径误差最小。

Ensemble prediction experiments of tracks of eight tropical cyclones occurring between 2004-2006 over the western Pacific are performed by using MM5 with five cumulus parameterization schemes. The results show that the predictions of the tracks of the tropical cyclones are sensitive to the selection of cumulus parameterization schemes. Each scheme has its own advantage and disadvantage, and the predications without cumulus parameterization schemes are not the worst, sometimes even better than the others. And all of the three ensemble methods improve the predictions of the tracks significantly, among which the ensemble method without parameterization schemes, the Grell, Betts-Miller and Kain-Fritsch schemes are the best.