首页|期刊导航|大气和海洋科学快报（英文版）|Short-term wind speed forecasting bias correction in the Hangzhou area of China based on a machine learning model

Short-term wind speed forecasting bias correction in the Hangzhou area of China based on a machine learning model

Yi Fang Yunfei Wu Fengmin Wu Yan Yan Qi Liu Nian Liu Jiangjiang Xia

大气和海洋科学快报（英文版）2023，Vol.16Issue(4)：37-44,8.

大气和海洋科学快报（英文版）2023，Vol.16Issue(4)：37-44,8.DOI:10.1016/j.aosl.2023.100339

Short-term wind speed forecasting bias correction in the Hangzhou area of China based on a machine learning model

Yi Fang ¹Yunfei Wu ²Fengmin Wu ³Yan Yan ⁴Qi Liu ⁵Nian Liu ⁵Jiangjiang Xia⁵

作者信息

1. Key Laboratory of Middle Atmosphere and Global Environment Observation,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing,China||College of Earth and Planetary Sciences,University of Chinese Academy of Sciences,Beijing,China
2. Key Laboratory of Middle Atmosphere and Global Environment Observation,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing,China
3. Zhejiang Institute of Meteorological Sciences,Hangzhou,China
4. 93110 Troops,People's Liberation Army of China,Beijing,China
5. Key Laboratory of Regional Climate-Environment for Temperate East Asia,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing,China||College of Earth and Planetary Sciences,University of Chinese Academy of Sciences,Beijing,China
折叠

摘要

Abstract

准确的风速预报具有重要的社会意义.在本研究中,使用名为WSFBC-XGB的XGBoost机器学习模型对中国浙江省杭州市自动气象站的短期风速预报误差进行校正.WSFBC-XGB使用本地数值天气预报系统的产品作为输入.将WSFBC-XGB校正的结果与传统MOS(模型输出统计)方法校正的结果进行了比较.结果表明:WSFBC-XGB预报风速的均方根误差(RMSE)/准确率(ACC)分别比NWP和MOS降低/提高了 26.1％和7.64％/35.6％和7.02％;对于90％的站点WSFBC-XGB的RMSE/ACC均小于/高于MOS.此外,采用平均杂质减少法对WSFBC-XGB的可解释性进行分析,以帮助用户增加对模型的信任.结果表明:10米风速(47.35％),10米风的经向分量(12.73％),日循环(9.97％)和1000百帕风的经向分量(7.45％)是前4个最重要的特征.WSFBC-XGB模型将有助于提高短期风速预报的准确性,为大型户外活动提供支持.

关键词

机器学习/极端梯度提升算法/风速/后处理/平均杂质减少

Key words

Machine learning/XGBoost algorithm/Wind speed/Postprocessing/Mean decrease in impurity

引用本文复制引用

Yi Fang,Yunfei Wu,Fengmin Wu,Yan Yan,Qi Liu,Nian Liu,Jiangjiang Xia..Short-term wind speed forecasting bias correction in the Hangzhou area of China based on a machine learning model[J].大气和海洋科学快报（英文版）,2023,16(4):37-44,8.

基金项目

This study was supported by the National Key Research and Devel-opment Program of China[grant number 2022YFF0802501]. （）

大气和海洋科学快报（英文版）

OACSCD

ISSN：1674-2834

访问量0

下载量0

段落导航