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
  • [21] DEVELOPMENT OF RAINFALL FORECASTING MODEL USING MACHINE LEARNING WITH SINGULAR SPECTRUM ANALYSIS
    Reddy, Pundru Chandra Shaker
    Sucharitha, Yadala
    Narayana, Goddumarri Surya
    IIUM ENGINEERING JOURNAL, 2022, 23 (01): : 172 - 186
  • [22] Improving voltage harmonics forecasting at a wind farm using deep learning techniques
    Kuyunani, E. M.
    Hasan, Ali N.
    Shongwe, T.
    PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2021,
  • [23] Deep learning model for flood probabilistic forecasting considering spatiotemporal rainfall distribution and hydrologic uncertainty
    Xiang, Xin
    Guo, Shenglian
    Li, Chenglong
    Sun, Bokai
    Liang, Zhiming
    JOURNAL OF HYDROLOGY, 2025, 655
  • [24] Forecasting water quality variable using deep learning and weighted averaging ensemble models
    Mohammad G. Zamani
    Mohammad Reza Nikoo
    Sina Jahanshahi
    Rahim Barzegar
    Amirreza Meydani
    Environmental Science and Pollution Research, 2023, 30 : 124316 - 124340
  • [25] Forecasting water quality variable using deep learning and weighted averaging ensemble models
    Zamani, Mohammad G.
    Nikoo, Mohammad Reza
    Jahanshahi, Sina
    Barzegar, Rahim
    Meydani, Amirreza
    ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2023, 30 (59) : 124245 - 124262
  • [26] Improving Deep Learning for Forecasting Accuracy in Financial Data
    Lin, Shih-Lin
    Huang, Hua-Wei
    DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2020, 2020
  • [27] Rainfall variability over multiple cities of India: analysis and forecasting using deep learning models
    Panda, Jagabandhu
    Nagar, Nistha
    Mukherjee, Asmita
    Bhattacharyya, Saugat
    Singh, Sanjeev
    EARTH SCIENCE INFORMATICS, 2024, 17 (02) : 1105 - 1124
  • [28] Forecasting Monthly Rainfall using Bio-Inspired Artificial Algae Deep Learning Network
    Kala, A.
    Vaidyanathan, S. Ganesh
    FLUCTUATION AND NOISE LETTERS, 2022, 21 (02):
  • [29] Rainfall variability over multiple cities of India: analysis and forecasting using deep learning models
    Jagabandhu Panda
    Nistha Nagar
    Asmita Mukherjee
    Saugat Bhattacharyya
    Sanjeev Singh
    Earth Science Informatics, 2024, 17 : 1105 - 1124
  • [30] Optimizing Physics Parameters for Heavy Rainfall Forecasting in the Kelani River Basin Using the WRF Model
    Perera, P.L.L.N.
    Neluwala, N.G.P.B.
    Wijetunge, J.J.
    Lecture Notes in Civil Engineering, 2024, 517 LNCE : 325 - 339