引入动态历史记忆模块，提升降水临近预报的准确性与稳定性。
When the Past Matters: FlashBack Memory for Precipitation Nowcasting
- 用动态检索历史状态增强循环模型的时空表征能力
- 在多个数据集上显著降低误差并减少漏报与误报
- 适合需要高精度长序列降水预测的研究与应用
精准的降水临近预报对防灾减灾和经济社会规划至关重要，但现有方法在高时空分辨率下常面临误报、漏报及长程依赖建模困难。为此，我们提出闪回记忆（FlashBack Memory, FB）模块，通过自适应融合门动态检索关键历史状态，增强基于循环神经网络模型的时空表征能力。将FB集成至PredRNN、PredRNNpp、MIM、MotionRNN和PredRNN-V2，在CIKM2017、Shanghai2020和SEVIR数据集上评估。实验表明，FB显著改善了均方误差（MSE）、平均绝对误差（MAE）、结构相似性（SSIM）和命中率（CSI）指标，尤其在高强度降雨和长序列预测中表现突出，同时减少误报与漏报，提升时间一致性与空间定位精度。该方法为循环模型提供了一种通用高效的记忆增强机制，全面提升了降水临近预报性能。
原文摘要 · Abstract (English)
Accurate precipitation nowcasting is crucial for disaster mitigation and socio-economic planning, yet existing methods often struggle with false alarms, missed events, and long range dependency modeling at high spatiotemporal resolution. To address these challenges, we propose FlashBack Memory (FB), a module that dynamically retrieves key historical states and integrates them via an adaptive fusion gate, enhancing the spatiotemporal representation capability of recurrent-based models. We incorporate FB into PredRNN, PredRNNpp, MIM, MotionRNN, and PredRNN-V2, and evaluate on CIKM2017, Shanghai2020, and SEVIR datasets. Experimental results demonstrate that FB significantly improves MSE, MAE, SSIM, and CSI metrics, particularly for high-intensity rainfall and long-sequence predictions, while reducing false alarms and missed events and enhancing temporal consistency and spatial localization. The proposed method provides a general and efficient memory enhancement mechanism, improving the overall performance of recurrent-based precipitation nowcasting models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。