本文已被：浏览 668次 下载 1781次
投稿时间：2008-01-30 修订日期：2008-10-30
投稿时间：2008-01-30 修订日期：2008-10-30
中文摘要: 以T213数值模式输出产品为基础，结合常规观测的降水资料，利用SVM方法，进行了大 量多因子的随机交叉验证，从而选出最优参数，建立了全国72个站点的降水预报模型，并用 独立的样本对预报模型进行了检验。再通过计算正、负样本的贴近度来分析预报因子，实现 了预报因子的筛选和降水预报模型的改进；检验结果表明：改进后的降水模型的预报结果优 于改进前的。实时业务试运行的结果也显示SVM模型的降水预报效果好于T213模式直接输出 的降水预报。
Abstract:Based on T213 NWP(Numerical Weather Prediction）model outputs and prec ipitation observations, cross validation is performed with random samples to fi n d the samples with best predictors and optimal parameters. The forecast models o f precipitation are established at 72 meteorological stations in China by the SV M (Support Vector Machine) statistical method. The models are verified with inde pendent samples. The predictors are selected and the precipitation forecast mode ls are improved by pressing close degree. Forecast experiments show that the imp roved models are better. The precipitation forecasted by SVM models is superi or to the precipitation of T213 DMO (direct model output) in real-time experimen ts.
keywords: support vector machine(SVM) method precipitation forecast pressing close degre e predictor
文章编号： 中图分类号： 文献标志码：
基金项目:“中国气象局数值模式创新基地”开放课题（2007）
| Author Name | Affiliation |
| Xiong Qiufen | CMA Training Centre, Beijing 100081 |
| Zeng Xiaoqing | Atmospheric Science Academy of La nzhou University |
引用文本：
熊秋芬,曾晓青,2008.SVM方法在降水预报中的应用及改进[J].气象,34(12):90-95.
Xiong Qiufen,Zeng Xiaoqing,2008.Application and Improvement of SVM Method in Precipitation For ecast [J].Meteor Mon,34(12):90-95.
熊秋芬,曾晓青,2008.SVM方法在降水预报中的应用及改进[J].气象,34(12):90-95.
Xiong Qiufen,Zeng Xiaoqing,2008.Application and Improvement of SVM Method in Precipitation For ecast [J].Meteor Mon,34(12):90-95.