OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting
This work addresses SST forecasting for climate modeling and disaster forecasting, with incremental improvements in attention mechanisms.
The paper tackled the challenge of predicting Sea Surface Temperature (SST) with nonlinear spatiotemporal dynamics by proposing OptFormer, which integrates phase-space reconstruction and optical flow-guided attention, achieving superior performance in accuracy and robustness on NOAA SST datasets.
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.