融合卷积、注意力与物理约束，提升海洋锋面预测精度与稳定性
CTP: A hybrid CNN-Transformer-PINN model for ocean front forecasting
- 结合CNN局部特征提取、Transformer长程时序建模与物理约束
- 在南海和黑潮区多步预测中显著提升准确率与F1分数
- 适合需要高物理一致性的海洋环境预测研究者
本文提出CTP框架，将卷积神经网络（CNN）、Transformer与物理信息神经网络（PINN）融合，用于海洋锋面预测。海洋锋面是不同水团间的动态界面，在海洋生物地球化学与物理过程中起关键作用。现有方法如LSTM、ConvLSTM和AttentionConv在多步预测中难以保持空间连续性与物理一致性。CTP通过局部空间编码、长程时序注意力与物理约束强化，有效解决该问题。基于1993至2020年南海（SCS）与黑潮（KUR）区域的实验结果表明，CTP在单步与多步预测中均达到当前最优性能，显著优于基线模型，在准确率、F1分数与时间稳定性方面均有明显提升。
原文摘要 · Abstract (English)
This paper proposes CTP, a novel deep learning framework that integrates convolutional neural network(CNN), Transformer architectures, and physics-informed neural network(PINN) for ocean front prediction. Ocean fronts, as dynamic interfaces between distinct water masses, play critical roles in marine biogeochemical and physical processes. Existing methods such as LSTM, ConvLSTM, and AttentionConv often struggle to maintain spatial continuity and physical consistency over multi-step forecasts. CTP addresses these challenges by combining localized spatial encoding, long-range temporal attention, and physical constraint enforcement. Experimental results across south China sea(SCS) and Kuroshio(KUR) regions from 1993 to 2020 demonstrate that CTP achieves state-of-the-art(SOTA) performance in both single-step and multi-step predictions, significantly outperforming baseline models in accuracy, $F_1$ score, and temporal stability.
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。