PCSDiff：面向实用业务中期降水预报的基于扩散的偏差校正与超分辨率

中文摘要 AI 辅助

中期降水预报受到持续系统性偏差、随预报时效增加的误差累积以及粗糙空间分辨率的损害，限制了其在洪水-干旱风险评估中的可靠性。现有的人工智能校正技术缺乏对多日动态偏差演变的专门建模和适当的气象约束，常常生成过度平滑的降雨结构，且无法满足业务部署需求。本工作提出PCSDiff，一个级联任务解耦的扩散框架，用于10天降水偏差校正和降尺度。为联合抵消时间误差漂移并重建物理上合理的局地降水细节，PCSDiff集成了降水强度感知多分支解码器（PIMD）模块，利用天气尺度-时间尺度特征进行动态多日误差缓解，随后采用两阶段条件扩散超分辨率模块恢复细尺度降水模式。在使用全球数据训练后，针对中国CMA-CRA观测进行评估，PCSDiff在3-10天预报时效内相对于原始ECMWF预报将均方根误差（RMSE）降低16.1%，并将 anomaly correlation coefficient（ACC）提升13.9%，且在一般和极端降水指标上均持续优于主流深度学习基线。得益于流式推理流水线，我们的方法实现了低延迟滚动预报，可满足实际气象业务需求。

英文摘要

Medium-range precipitation forecasts are impaired by persistent systematic biases, lead-time-dependent error accumulation, and coarse spatial resolution, restricting their reliability for flood-drought risk assessment. Existing AI correction techniques lack dedicated modeling for multi-day dynamic bias evolution and proper meteorological constraints, often generating over-smoothed rainfall structures, and cannot meet operational deployment demands. This work introduces PCSDiff, a cascaded task-decoupled diffusion framework targeting 10-day precipitation bias correction and downscaling. To jointly counteract temporal error drifts and reconstruct physically plausible local precipitation details, PCSDiff integrates the Precipitation Intensity-aware Multi-branch Decoder (PIMD) module for dynamic multi-day error mitigation using synoptic-temporal features, followed by a two-phase conditional diffusion super-resolution module to restore fine-scale precipitation patterns. Evaluated against CMA-CRA observations over China after global-data training, PCSDiff cuts RMSE by 16.1% and lifts ACC by 13.9% relative to raw ECMWF forecasts at 3-10-day lead times, and consistently outperforms mainstream deep-learning baselines on both general and extreme-precipitation metrics. Benefiting from a streaming inference pipeline, our method achieves low-latency rolling forecasting for practical meteorological operations.

发表机构

• Tsinghua University（清华大学）
• Huawei Technologies Co., Ltd（华为技术有限公司）
• ETH Zürich（苏黎世联邦理工学院）
• Beijing Forestry University（北京林业大学）
• National Climate Centre, China Meteorological Administration（中国气象局国家气候中心）
• National Institute of Natural Hazards, Ministry of Emergency Management of China（中国应急管理部国家自然灾害防治研究院）

机构由 AI 辅助整理，请以论文原文为准。