Improving the heavy rainfall forecasting using a weighted deep learning model

被引:9
|
作者
Chen, Yutong [1 ,2 ,3 ]
Huang, Gang [1 ,2 ,3 ]
Wang, Ya [1 ]
Tao, Weichen [1 ]
Tian, Qun [4 ]
Yang, Kai [1 ]
Zheng, Jiangshan [5 ]
He, Hubin [6 ]
机构
[1] Chinese Acad Sci, Inst Atmospher Phys, State Key Lab Numer Modeling Atmospher Sci & Geop, Beijing, Peoples R China
[2] Qingdao Natl Lab Marine Sci & Technol, Lab Reg Oceanog & Numer Modeling, Qingdao, Peoples R China
[3] Univ Chinese Acad Sci, Coll Earth & Planetary Sci, Beijing, Peoples R China
[4] Guangzhou Inst Trop & Marine Meteorol, Guangdong Prov Key Lab Reg Numer Weather Predict, CMA, Guangzhou, Peoples R China
[5] Design & Res Inst Co Ltd, Shanghai Invest, Shanghai, Peoples R China
[6] Zhejiang Inst Communicat Co Ltd, Hangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
bias correction; deep learning; extremely heavy rainfall; imbalanced data; ECMWF; Henan; WEATHER PREDICTION MODELS; PRECIPITATION FORECASTS; UNCERTAINTY; MOS;
D O I
10.3389/fenvs.2023.1116672
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Weather forecasting has been playing an important role in socio-economics. However, operational numerical weather prediction (NWP) is insufficiently accurate in terms of precipitation forecasting, especially for heavy rainfalls. Previous works on NWP bias correction utilizing deep learning (DL) methods mostly focused on a local region, and the China-wide precipitation forecast correction had not been attempted. Meanwhile, earlier studies imposed no particular focus on strong rainfalls despite their severe catastrophic impacts. In this study, we propose a DL model called weighted U-Net (WU-Net) that incorporates sample weights for various precipitation events to improve the forecasts of intensive precipitation in China. It is found that WU-Net can further improve the forecasting skill of heaviest rainfall comparing with the ordinary U-Net and ECMWF-IFS. Further analysis shows that this improvement increases with growing lead time, and distributes mainly in the eastern parts of China. This study suggests that a DL model considering the imbalance of the meteorological data could further improve the precipitation forecasting generated by numerical weather prediction.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Deep Learning for Improving Numerical Weather Prediction of Heavy Rainfall
    Hess, Philipp
    Boers, Niklas
    JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS, 2022, 14 (03)
  • [2] Improving Ocean Forecasting Using Deep Learning and Numerical Model Integration
    Choi, Youngjin
    Park, Youngmin
    Hwang, Jaedong
    Jeong, Kijune
    Kim, Euihyun
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2022, 10 (04)
  • [3] Deep learning model for heavy rainfall nowcasting in South Korea
    Oh, Seok-Geun
    Son, Seok-Woo
    Kim, Young -Ha
    Park, Chanil
    Ko, Jihoon
    Shin, Kijung
    Ha, Ji-Hoon
    Lee, Hyesook
    WEATHER AND CLIMATE EXTREMES, 2024, 44
  • [4] Multi-step rainfall forecasting using deep learning approach
    Narejo, Sanam
    Jawaid, Muhammad Moazzam
    Talpur, Shahnawaz
    Baloch, Rizwan
    Pasero, Eros Gian Alessandro
    PEERJ COMPUTER SCIENCE, 2021,
  • [5] Numerical Prediction of Heavy Rainfall Using Weather and Research Forecasting Model
    Kita, Masato
    Kawahara, Yoshihisa
    Tsubaki, Ryota
    Ushiyama, Tomoki
    PROCEEDINGS OF THE 35TH IAHR WORLD CONGRESS, VOLS III AND IV, 2013,
  • [6] A Model for Rainfall Forecasting using Distinct Machine Learning Algorithm
    Upadhye, Sachin
    Agrawal, Lalit
    INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING, 2022, 13 (05): : 1220 - 1226
  • [7] Advance drought prediction through rainfall forecasting with hybrid deep learning model
    Gupta, Brij B.
    Gaurav, Akshat
    Attar, Razaz Waheeb
    Arya, Varsha
    Bansal, Shavi
    Alhomoud, Ahmed
    Chui, Kwok Tai
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [8] Analysis of rainfall and temperature using deep learning model
    Choudhary, Surendra Singh
    Ghosh, S. K.
    THEORETICAL AND APPLIED CLIMATOLOGY, 2023, 153 (1-2) : 755 - 770
  • [9] Analysis of rainfall and temperature using deep learning model
    Surendra Singh Choudhary
    S. K. Ghosh
    Theoretical and Applied Climatology, 2023, 153 : 755 - 770
  • [10] Weighted Deep Learning Approach For Better Forecasting
    Hansun, Seng
    Putri, Farica Perdana
    JOURNAL OF APPLIED SCIENCE AND ENGINEERING, 2023, 27 (04): : 2351 - 2358