A systematic approach to developing an effective AI-based bias correction model

This study introduces ReSA-ConvLSTM, an AI framework for systematic bias correction in numerical weather prediction. We propose three innovations by integrating dynamic climatological normalization, ConvLSTM with temporal causality constraints, and residual self-attention mechanisms. The model establishes a physics-aware nonlinear mapping between ECMWF forecasts and ERA5 reanalysis data. Using 41 years (1981–2021) of global atmospheric data, the framework reduces systematic biases in T2m, U10 and SLP, achieving a maximum reduction in RMSE of up to 20% for the 7-day T2m forecasts compared to operational ECMWF outputs. The lightweight architecture (10.6M parameters) enables efficient generalization to multiple variables and downstream applications, reducing the retraining time by 85% for cross-variable correction while improving the ocean model skill through bias-corrected boundary conditions. The ablation experiments demonstrate that our innovations significantly improve the model’s correction performance, suggesting that incorporating variable characteristics into the model helps enhance forecasting skills. 本研究提出了一种物理引导设计的AI偏差订正框架ReSA-ConvLSTM, 通过动态气候归一化,带时间因果约束的ConvLSTM和残差自注意力机制三大创新, 实现对ECMWF数值预报的系统性偏差订正.该模型以ERA5再分析资料为真值, 在41年全球大气数据上训练, 显著提升了2米气温,10米风场和海平面气压的预报精度, 均方根误差最高降低20%, 模型参数量仅1060万, 具备轻量,高效,易扩展的特点.消融实验验证了各组件的有效性, 下游应用表明其可快速迁移至多变量订正并提升海洋模式模拟能力.