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
  • [41] FORECASTING MODEL OF RAINFALL
    Sharma, M. K.
    Pandey, Anshula
    INTERNATIONAL JOURNAL OF AGRICULTURAL AND STATISTICAL SCIENCES, 2018, 14 (01): : 139 - 143
  • [42] Analysis and Forecasting of Temporal Rainfall Variability Over Hundred Indian Cities Using Deep Learning Approaches
    Singh, Sanjeev
    Mukherjee, Asmita
    Panda, Jagabandhu
    Choudhury, Animesh
    Bhattacharyya, Saugat
    EARTH SYSTEMS AND ENVIRONMENT, 2024, 8 (03) : 599 - 625
  • [43] Tropical cyclone intensity forecasting using model knowledge guided deep learning model
    Wang, Chong
    Li, Xiaofeng
    Zheng, Gang
    ENVIRONMENTAL RESEARCH LETTERS, 2024, 19 (02)
  • [44] A short term multistep forecasting model for photovoltaic generation using deep learning model
    Dinesh, Lakshmi P.
    Khafaf, Nameer Al
    McGrath, Brendan
    Sustainable Operations and Computers, 2025, 6 : 34 - 46
  • [45] Estimating Rainfall Intensity Using an Image-Based Deep Learning Model
    Yin, Hang
    Zheng, Feifei
    Duan, Huan-Feng
    Savic, Dragan
    Kapelan, Zoran
    ENGINEERING, 2023, 21 : 162 - 174
  • [46] A Study on Local Heavy Rainfall Forecasting Method Using Convolutional LSTM
    Takehana, Haruki
    Yanagawa, Yoshiki
    Ozaki, Astuo
    Oshima, Kazuyoshi
    2021 36TH INTERNATIONAL TECHNICAL CONFERENCE ON CIRCUITS/SYSTEMS, COMPUTERS AND COMMUNICATIONS (ITC-CSCC), 2021,
  • [47] An Optimal Weighted Combined Model Coupled with Feature Reconstruction and Deep Learning for Multivariate Stock Index Forecasting
    Wang, Jujie
    Liao, Yinan
    Zhuang, Zhenzhen
    Gao, Dongming
    MATHEMATICS, 2021, 9 (21)
  • [48] A SURVEY OF RAINFALL PREDICTION USING DEEP LEARNING
    Hussain, Jamal
    Zoremsanga, Chawngthu
    2021 3RD INTERNATIONAL CONFERENCE ON ELECTRICAL, CONTROL AND INSTRUMENTATION ENGINEERING (IEEE ICECIE'2021), 2021,
  • [49] A novel forecasting strategy for improving the performance of deep learning models
    Livieris, Ioannis E.
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 230
  • [50] DLENSO: A Deep Learning ENSO Forecasting Model
    He, Dandan
    Lin, Pengfei
    Liu, Hailong
    Ding, Lei
    Jiang, Jinrong
    PRICAI 2019: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II, 2019, 11671 : 12 - 23