发表机构
Southeast University; Beijing Fengyun Meteorological Science and Technology Development Co., Ltd.; Beihang University（东南大学; 北京风云气象科技发展有限公司; 北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PrecipJEPA通过结合预测路径与辅助JEPA正则化，利用运动源渲染实现降水临近预报，在SEVIR和MeteoNet上显著提升高阈值CSI。
AI 中文摘要
长期降水临近预报需要在建模雷达回波演变的同时保留局部高强度结构。近期针对雷达的特定研究推动了位置感知预测以及将回波位移与强度变化分离的动机。然而，现有编码器主要从最终预测误差中学习历史表示。我们提出了PrecipJEPA，它将结构化预测路径与辅助路径相结合，该辅助路径从观测到的雷达历史中丰富其编码器。在预测路径中，在线编码器首先将观测转换为时空令牌。任务驱动未来状态预测器（TFP）将这些令牌与近期动态摘要和时空查询相结合，以构建未来雷达状态。并行运动源渲染器（PMSR）将这些状态解码为运动场和源汇场，将最新观测转换为未来帧。在联合训练期间，历史掩蔽JEPA（H-JEPA）在辅助路径上运行，从可见上下文预测掩蔽的历史特征，直接监督来自观测序列的同一在线编码器。在SEVIR和MeteoNet上的实验表明，与最强基线相比，PrecipJEPA在最高阈值CSI上分别提高了118.6%和35.1%，同时在3小时预报期间保持了最高的平均CSI。
英文摘要
Long-term precipitation nowcasting requires modeling radar-echo evolution while preserving localized high-intensity structures. Recent radar-specific studies motivate location-aware prediction and separating echo displacement from intensity change. However existing encoders learn historical representations mainly from final forecast errors. We propose PrecipJEPA, which couples a structured forecasting path with an auxiliary path that enriches its encoder from observed radar history. In the forecasting path, an online encoder first converts the observations into spatiotemporal tokens. The Task-Driven Future-State Predictor (TFP) combines these tokens with a recent-dynamics summary and spatiotemporal queries to construct future radar states. The Parallel Motion-Source Renderer (PMSR) decodes these states into motion and source-sink fields that transform the latest observation into future frames. During joint training, the History-Masked JEPA (H-JEPA) operates on the auxiliary path to predict masked historical features from visible context, directly supervising the same online encoder from the observed sequence. Experiments on SEVIR and MeteoNet show that PrecipJEPA improves highest-threshold CSI by 118.6% and 35.1%, respectively, over the strongest baselines, while maintaining the highest mean CSI throughout the 3-hour forecast.
Comments5 pages, 3 figures
