AI Heap
Published on

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

arXiv:2502.00338 - [arXiv,PDF]
Authors
  • Name
    Yuan Gao
  • Name
    Hao Wu
  • Name
    Ruiqi Shu
  • Name
    Huanshuo Dong
  • Name
    Fan Xu
  • Name
    Rui Ray Chen
  • Name
    Yibo Yan
  • Name
    Qingsong Wen
  • Name
    Xuming Hu
  • Name
    Kun Wang
  • Name
    Jiahao Wu
  • Name
    Qing Li
  • Name
    Hui Xiong
  • Name
    Xiaomeng Huang
  • Affiliation
    University of Science and Technology
  • Affiliation
    Tsinghua University
  • Affiliation
    Peking University
  • Affiliation
    Zhejiang University
  • Affiliation
    Fudan University
  • Affiliation
    National University of Singapore
  • Affiliation
    Shanghai Jiao Tong University
  • Affiliation
    Beijing Institute of Technology
  • Affiliation
    Nanjing University
  • Affiliation
    Harbin Institute of Technology
  • Affiliation
    Xi'an Jiaotong University
  • Affiliation
    University of Electronic Science and Technology of China
  • Affiliation
    Rutgers University
  • Affiliation
    University of California, Berkeley
Accurate weather forecasts are important for disaster prevention, agricultural planning, etc. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive and fail to fully leverage rapidly growing historical data. In recent years, deep learning models have made significant progress in weather forecasting, but challenges remain, such as balancing global and regional high-resolution forecasts, excessive smoothing in extreme event predictions, and insufficient dynamic system modeling. To address these issues, this paper proposes a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks. By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region to capture local high-frequency features. We introduce an adaptive messaging mechanism, using dynamic gating units to deeply integrate node and edge features for more accurate extreme event forecasting. For high-resolution regional forecasts, we propose a neural nested grid method to mitigate boundary information loss. Experimental results show that OneForecast performs excellently across global to regional scales and short-term to long-term forecasts, especially in extreme event predictions. Codes link https://github.com/YuanGao-YG/OneForecast.