| 处理非线性分类和回归问题的一种新方法 (Ⅱ)——支持向量机方法在天气预报中的应用 |
| |
| 引用本文： | 冯汉中,陈永义.处理非线性分类和回归问题的一种新方法 (Ⅱ)——支持向量机方法在天气预报中的应用[J].应用气象学报,2004,15(3):355-365. |
| |
| 作者姓名： | 冯汉中 陈永义 |
| |
| 作者单位： | 1.成都气象中心, 成都 610071 |
| |
| 基金项目： | 国家自然科学基金资助 ( 60 0 72 0 0 6) |
| |
| 摘 要： | 将SVM（Support Vector Machine）分类和回归方法首次应用于气象预报试验。利用1990~2000年4~9月ECMWF北半球的500 hPa高度、850 hPa温度、地面气压的00:00 UTC分析场资料，建立四川盆地分区面雨量有无大于15 mm的SVM分类推理模型、四川盆地内单站气温的SVM回归推理模型，进行相应的预报试验，试验结果显示对应的SVM推理模型具有良好的预报能力。
|
| 关 键 词： | 支持向量机（SVM） 模式识别 回归估计 降水分类预报 温度预报 |
| 收稿时间： | 2003-01-25 |
| 修稿时间： | 2003年1月25日 |
A NEW METHOD FOR NON-LINEAR CLASSIFY AND NON-LINEAR REGRESSION Ⅱ:APPLICATION OF SUPPORT VECTOR MACHINE TO WEATHER FORECAST |
| |
| Feng Hanzhong.A NEW METHOD FOR NON-LINEAR CLASSIFY AND NON-LINEAR REGRESSION Ⅱ:APPLICATION OF SUPPORT VECTOR MACHINE TO WEATHER FORECAST[J].Quarterly Journal of Applied Meteorology,2004,15(3):355-365. |
| |
| Authors: | Feng Hanzhong |
| |
| Institution: | 1.Chengdu Meteorological Center, Chengdu 6100712.Training Center of China Meteorological Administration, Beijing 100081 |
| |
| Abstract: | A novel weather forecast method using the support vector machine (SVM) is introduced. Both of SVM model of area rainfall categorical forecast of 15 mm excess and SVM model of single-station temperature regression in Sichuan basin are built upon ECMWF analysis fields of 500 hPa height, 850 hPa temperature, and sea level pressure from April to September through 1990-2000. Extensive experiments are performed with performances evaluated by the Threat Scores (TS) or Correlation Coefficient. Empirical results demonstrate much improved performance compared with those given by standard statistic analysis and forecast methods. |
| |
| Keywords: | Support vector machines (SVM) Pattern recognition Regression estimation Rainfall categorical forecast Temperature forecast |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《应用气象学报》浏览原始摘要信息 |
| 点击此处可从《应用气象学报》下载免费的PDF全文 |
