用光流引导注意力，提升海温预测精度与鲁棒性
OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting
- 结合相空间重构与光流引导注意力，捕捉动态变化区域
- 在多尺度海温数据上显著优于现有基线模型
- 适合气候建模、灾害预警等需要长期预测的场景
海表温度（SST）预测在气候建模和灾害预警中至关重要，但因其非线性时空动态和长时程预测挑战而难以实现。为此，我们提出OptFormer，一种融合相空间重构与光流引导运动感知注意力机制的编码器-解码器模型。不同于传统注意力机制，该方法利用帧间运动线索突出空间场中的相对变化，使模型更聚焦于动态区域，有效捕捉长时序依赖关系。在NOAA SST数据集上的多尺度实验表明，采用1:1训练-预测设置时，OptFormer在准确性和鲁棒性方面均显著超越现有基线模型。
原文摘要 · Abstract (English)
Sea Surface Temperature (SST) prediction plays a vital role in climate modeling and disaster forecasting. However, it remains challenging due to its nonlinear spatiotemporal dynamics and extended prediction horizons. To address this, we propose OptFormer, a novel encoder-decoder model that integrates phase-space reconstruction with a motion-aware attention mechanism guided by optical flow. Unlike conventional attention, our approach leverages inter-frame motion cues to highlight relative changes in the spatial field, allowing the model to focus on dynamic regions and capture long-range temporal dependencies more effectively. Experiments on NOAA SST datasets across multiple spatial scales demonstrate that OptFormer achieves superior performance under a 1:1 training-to-prediction setting, significantly outperforming existing baselines in accuracy and robustness.
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。