Scholarlink

<p>Optimizing numerical weather prediction (NWP) or correcting its errors using data-driven machine learning (ML) methods is a highly challenging task. To tackle this problem, we propose a coupled ML–NWP optimization framework that incorporates data-driven model bias calibration directly into NWP integration loops. By reimplementing the dynamic solver and physical parameterizations of the Weather Research and Forecasting (WRF) model in Python, we develop a tensor-based PyWRF model that fully supports automatic differentiation in PyTorch. A single-column neural network (NN) is coupled with PyWRF to enable observation-guided backward gradient propagation, facilitating feedback between observations and integration steps to modulate specific model variables. During numerical integration, online coupled training of the NN with PyWRF is achieved through local gradient masking, truncated back-propagation over a finite number of steps, and skip-connection-based variable transfer. Eight mesoscale precipitation events over East China were selected to train and evaluate the coupled model. The results demonstrate that the model trained on limited observational data within this framework exhibits robust generalization capability. Comparative experiments indicate that the proposed framework outperforms standalone NWP and conventional single-step artificial intelligence (AI) correction methods in forecast accuracy. This study provides a pathway for next-generation physics–data–intelligence weather forecasting systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel ML–NWP Coupled Optimization Approach on a Reconstructed WRF Model

  • 期刊论文

  • 发表日期：

    2026年6月25日

查看全文
  • Hai Chu,
  • Yuan Cao,
  • Rui Wang,
  • Jianming Xu,
  • Lei Chen,
  • Xuliang Fan,
  • Shiqi Chen,
  • Jianhai Guo,
  • Junjing Wu

摘要

Optimizing numerical weather prediction (NWP) or correcting its errors using data-driven machine learning (ML) methods is a highly challenging task. To tackle this problem, we propose a coupled ML–NWP optimization framework that incorporates data-driven model bias calibration directly into NWP integration loops. By reimplementing the dynamic solver and physical parameterizations of the Weather Research and Forecasting (WRF) model in Python, we develop a tensor-based PyWRF model that fully supports automatic differentiation in PyTorch. A single-column neural network (NN) is coupled with PyWRF to enable observation-guided backward gradient propagation, facilitating feedback between observations and integration steps to modulate specific model variables. During numerical integration, online coupled training of the NN with PyWRF is achieved through local gradient masking, truncated back-propagation over a finite number of steps, and skip-connection-based variable transfer. Eight mesoscale precipitation events over East China were selected to train and evaluate the coupled model. The results demonstrate that the model trained on limited observational data within this framework exhibits robust generalization capability. Comparative experiments indicate that the proposed framework outperforms standalone NWP and conventional single-step artificial intelligence (AI) correction methods in forecast accuracy. This study provides a pathway for next-generation physics–data–intelligence weather forecasting systems.