用分形扫描增强海冰浓度预测，提升时间连续性和边界精度
Frequency-Enhanced Hilbert Scanning Mamba for Short-Term Arctic Sea Ice Concentration Prediction
- 3D分形扫描保持时空邻近性，序列顺序对应真实空间位置
- 小波变换放大高频细节，提升边缘重建能力，误差降低12.3%
- 适合需要高精度短期海冰预测的气候与极地研究者
尽管Mamba模型具备高效的序列建模能力，但原始版本在北极海冰浓度（SIC）预测中难以捕捉时间相关性与边界细节。为此，本文提出频率增强型分形扫描Mamba框架（FH-Mamba）用于短期北极海冰浓度预测。具体而言，引入一种3D分形扫描机制，沿保持局部性的路径遍历三维时空网格，确保展平序列中相邻索引对应于空间和时间维度上的邻近体素。同时，结合小波变换以增强高频细节，并设计混合洗牌注意力模块，自适应融合序列与频率特征。在OSI-450a1和AMSR2数据集上的实验表明，相较于现有先进基线，FH-Mamba取得更优预测性能。结果验证了分形扫描与频率感知注意力在提升时间一致性与边缘重建方面的有效性。代码已公开于https://github.com/oucailab/FH-Mamba。
原文摘要 · Abstract (English)
While Mamba models offer efficient sequence modeling, vanilla versions struggle with temporal correlations and boundary details in Arctic sea ice concentration (SIC) prediction. To address these limitations, we propose Frequency-enhanced Hilbert scanning Mamba Framework (FH-Mamba) for short-term Arctic SIC prediction. Specifically, we introduce a 3D Hilbert scan mechanism that traverses the 3D spatiotemporal grid along a locality-preserving path, ensuring that adjacent indices in the flattened sequence correspond to neighboring voxels in both spatial and temporal dimensions. Additionally, we incorporate wavelet transform to amplify high-frequency details and we also design a Hybrid Shuffle Attention module to adaptively aggregate sequence and frequency features. Experiments conducted on the OSI-450a1 and AMSR2 datasets demonstrate that our FH-Mamba achieves superior prediction performance compared with state-of-the-art baselines. The results confirm the effectiveness of Hilbert scanning and frequency-aware attention in improving both temporal consistency and edge reconstruction for Arctic SIC forecasting. Our codes are publicly available at https://github.com/oucailab/FH-Mamba.
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。