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

被引：0
|
作者：
Yi Fang [1 ,2 ]
Yunfei Wu [1 ]
Fengmin Wu [3 ]
Yan Yan [4 ]
Qi Liu [5 ,2 ]
Nian Liu [5 ,2 ]
Jiangjiang Xia [5 ,2 ]
机构：
[1] Key Laboratory of Middle Atmosphere and Global Environment Observaaon,Institute of Atmospheric Physics,Chinese Academy of Sciences
[2] College of Earth and Planetary Sciences,University of Chinese Academy of Sciences
[3] Zhejiang Insatute of Meteorological Sciences
[4] 93110 Troops,People's Liberation Army of China
[5] Key Laboratory of Regional Climate-Environment for Temperate East Asia,Institute of Atmospheric Physics,Chinese Academy of Sciences
来源：
Atmospheric and Oceanic Science Letters | 2023年 / 16卷 / 04期
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;
D O I：
暂无
中图分类号：
P457.5 [风预报];
学科分类号：
0706 ; 070601 ;
摘要：
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:WSFBCXGB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.
引用
收藏
页码：39 / 46
页数：8
相关论文
共 50 条
  • [41] A hybrid method for short-term wind speed forecasting based on Bayesian optimization and error correction
    Guo, Xiuting
    Zhu, Changsheng
    Hao, Jie
    Zhang, Shengcai
    Zhu, Lina
    [J]. JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY, 2021, 13 (03)
  • [42] Short-Term Wind Power Forecasting by Advanced Machine Learning Models
    Li, Yun-Lun
    Zhu, Zheng-An
    Chang, Yun-Kai
    Chiang, Chen-Kuo
    [J]. 2020 INTERNATIONAL SYMPOSIUM ON COMPUTER, CONSUMER AND CONTROL (IS3C 2020), 2021, : 412 - 415
  • [43] A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network
    Xie, Anqi
    Yang, Hao
    Chen, Jing
    Sheng, Li
    Zhang, Qian
    [J]. ATMOSPHERE, 2021, 12 (05)
  • [44] Short-term Wind Speed Forecasting Based on an EEMD-CAPSO-RVM Model
    Zang, Haixiang
    Liang, Zhi
    Guo, Mian
    Qian, Zeyu
    Wei, Zhinong
    Sun, Guoqiang
    [J]. 2016 IEEE PES ASIA-PACIFIC POWER AND ENERGY ENGINEERING CONFERENCE (APPEEC), 2016, : 439 - 443
  • [45] Short-term wind speed forecasting model based on ANN with statistical feature parameters
    Ioakimidis, Christos S.
    Dallas, Panagiotis I.
    Genikomsakis, Konstantinos N.
    Lopez, Sergio
    [J]. IECON 2015 - 41ST ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2015, : 971 - 976
  • [46] A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning
    Xu, Yuanyuan
    Yang, Genke
    [J]. COMPLEXITY, 2020, 2020
  • [47] Short-Term Wind Speed Forecasting Based on the EEMD-GS-GRU Model
    Yao, Huaming
    Tan, Yongjie
    Hou, Jiachen
    Liu, Yaru
    Zhao, Xin
    Wang, Xianxun
    [J]. ATMOSPHERE, 2023, 14 (04)
  • [48] A Short-term Wind Speed Forecasting Model Based on Improved QPSO Optimizing LSSVM
    Hu, Zhiyuan
    Liu, Qunying
    Tian, Yunxiang
    Liao, Yongfeng
    [J]. 2014 INTERNATIONAL CONFERENCE ON POWER SYSTEM TECHNOLOGY (POWERCON), 2014,
  • [49] Short-Term Wind Speed Forecasting Based on Information of Neighboring Wind Farms
    Wang, Zhongju
    Zhang, Jing
    Zhang, Yu
    Huang, Chao
    Wang, Long
    [J]. IEEE ACCESS, 2020, 8 : 16760 - 16770
  • [50] Short-term wind power combination forecasting method based on wind speed correction of numerical weather prediction
    Wang, Siyuan
    Liu, Haiguang
    Yu, Guangzheng
    [J]. FRONTIERS IN ENERGY RESEARCH, 2024, 12
12345