| 基于数值预报和随机森林算法的强对流天气分类预报技术 |
| |
| 引用本文： | 李文娟,赵放,郦敏杰,陈列,彭霞云.基于数值预报和随机森林算法的强对流天气分类预报技术[J].气象,2018,44(12):1555-1564. |
| |
| 作者姓名： | 李文娟 赵放 郦敏杰 陈列 彭霞云 |
| |
| 作者单位： | 浙江省气象台，杭州 310017,浙江省气象台，杭州 310017,浙江省杭州市气象台，杭州 310057,浙江省气象台，杭州 310017,浙江省气象台，杭州 310017 |
| |
| 基金项目： | 国家气象中心关键技术项目［YBGJXM（2018）02 13］和浙江省科技厅重点项目(2017C03035)共同资助 |
| |
| 摘 要： | 随机森林算法是当前得到较为广泛应用的机器学习方法之一,有着很高的预测精度,训练结果稳定,泛化能力强,解决多分类问题有明显优势。本文将随机森林算法应用于强对流的潜势预测和分类,分短时强降水、雷暴大风、冰雹和无强对流四种类别,基于2005—2016年NCEP 1°×1°再分析资料计算的对流指数和物理量,开展强对流天气的分类训练、0～12 h预报和检验,经2015—2016年独立测试样本检验表明,针对强对流发生站点的点对点检验,整体误判率为21. 9%,85次强对流过程基本无漏报,模型尤其适用于较大范围强对流天气。随机森林算法筛选的因子物理意义较为明确,和主观预报经验基本相符,模型准确率高,可用于日常业务。
|
| 关 键 词： | 强对流分类，对流指数，物理量，随机森林 |
| 收稿时间： | 2017/9/15 0:00:00 |
| 修稿时间： | 2018/3/14 0:00:00 |
Forecasting and Classification of Severe Convective Weather Based on Numerical Forecast and Random Forest Algorithm |
| |
| LI Wenjuan,ZHAO Fang,LI Minjie,CHEN Lie and PENG Xiayun.Forecasting and Classification of Severe Convective Weather Based on Numerical Forecast and Random Forest Algorithm[J].Meteorological Monthly,2018,44(12):1555-1564. |
| |
| Authors: | LI Wenjuan ZHAO Fang LI Minjie CHEN Lie and PENG Xiayun |
| |
| Institution: | Zhejiang Meteorological Observatory, Hangzhou 310017,Zhejiang Meteorological Observatory, Hangzhou 310017,Hangzhou Meteorological Observatory of Zhejiang Province, Hangzhou 310057,Zhejiang Meteorological Observatory, Hangzhou 310017 and Zhejiang Meteorological Observatory, Hangzhou 310017 |
| |
| Abstract: | The random forest algorithm is currently one of the more widely used machine learning methods, featuring high prediction accuracy, stable training results and generalization ability, and has obvious advantages in solving the problem of multi classification. This paper applies the random forest algorithm to the prediction and classification of severe convective weather, which is divided into four categories: short time heavy rainfall, thunderstorm gale, hail and no severe convection. Then, based on the data of convection index and physics calculated from the NCEP data of 2005-2016, the training, 0-12 h forecasting and testing of classified severe convection are carried out. The results show that the whole misjudgment rate is 21.9% that is calculated out of the independent data of 2015-2016. It has almost no omission in 85 examples of severe convective weather and the model is especially suitable for larger range of severe convective weather. The physical meaning of the factors used in random forest algorithm is relatively clear, and basically consistent with the subjective forecasting experience. It can be used in daily forecasting operation. |
| |
| Keywords: | severe convection classification convective index physical quantity parameter random forest (RF) |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《气象》浏览原始摘要信息 |
| 点击此处可从《气象》下载免费的PDF全文 |
|
