Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yin, Gong, Chunlin, Xu, Zhuozhen, Zhang, Lehan, Wu, Xiang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.06078
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918280985313280
author Wang, Yin
Gong, Chunlin
Xu, Zhuozhen
Zhang, Lehan
Wu, Xiang
author_facet Wang, Yin
Gong, Chunlin
Xu, Zhuozhen
Zhang, Lehan
Wu, Xiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06078
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting
Wang, Yin
Gong, Chunlin
Xu, Zhuozhen
Zhang, Lehan
Wu, Xiang
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
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.
title OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting
topic Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2601.06078