单变量深度学习在有效波高预报中的局限性研究
On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting
查看机构详情
- Ludong University（鲁东大学）
- Dalian Maritime University（大连海事大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究系统评估五种深度学习架构在单变量有效波高预报中的表现，发现架构差异对误差影响远小于跨浮标方差，持续性预报已捕获主要信号，架构工程收益递减，建议未来转向多变量方法。
中文摘要 AI 辅助
本研究对五种深度学习架构（DLinear、LSTM、PatchTST、ResAttLstm和Mamba2）以及九种上下文长度（1-168小时）进行了系统的超参数搜索，用于NDBC浮标41009上的单站有效波高（Hs）预报，随后在包含47个浮标、37年数据的语料库上对最佳配置进行了重新评估。五种架构系列在多浮标评估中收敛到相近的性能水平（系列间标准差=0.0014 m²，占总均值的0.8%），这一差异远小于不同浮标语料库之间4.83倍的跨数据集MSE变化。所有多浮标试验均优于持续性预报（平均技能得分+0.062），但没有任何一种架构能持续优于其他架构。在单浮标实验中，技能在12-24小时达到峰值，此时五次试验低于持续性预报，各系列Q4/Q3测试MSE比率范围在2.4至2.6之间，且对于最极端的1%波浪，深度模型表现不如持续性预报。这些发现与以下解释一致：持续性预报已捕获单变量Hs中的主要线性惯性信号，且在此单变量输入设置下，架构工程已进入收益递减阶段：跨浮标方差（而非模型类别）主导了预报误差。未来工作应优先考虑大气协变量、零样本跨浮标迁移以及将Hs分解为涌浪和风浪分量。通过为单变量Hs模型能实现和不能实现的目标建立严格的参考基线，本研究为未来多变量和物理信息方法的校准提供了基准，并为中纬度风暴主导和混合涌浪环境中的轻量级浮标级预报提供了实用指导。
英文摘要
This study conducts a systematic hyperparameter search across five deep learning architectures, DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2, and nine context lengths (1-168 h) for single-station significant wave height (Hs) forecasting on NDBC buoy 41009, followed by re-evaluation of the best configurations on a 47-buoy, 37-year corpus. The five families converge to a common performance level on the multi-buoy evaluation (between-family SD = 0.0014 m^2, 0.8% of the grand mean), a spread dwarfed by the 4.83x cross-dataset MSE shift between buoy corpora. All multi-buoy trials beat persistence (mean skill +0.062), but no architecture consistently outperforms the others. On the single-buoy experiment, skill peaks at 12-24 h where five trials fall below persistence, per-family Q4/Q3 test MSE ratios range from 2.4 to 2.6, and deep models underperform persistence for the most extreme 1% of waves. These findings are consistent with the interpretation that persistence already captures the dominant linear-inertial signal in univariate Hs, and that architecture engineering under this univariate input setting has reached diminishing returns: cross-buoy variance, not model class, dominates forecast error. Future work should prioritise atmospheric covariates, zero-shot cross-buoy transfer, and decomposition of Hs into swell and wind-sea components. By establishing a rigorous reference baseline for what univariate Hs models can and cannot achieve, this study provides a benchmark against which future multivariate and physics-informed approaches can be calibrated, and offers practical guidance for lightweight buoy-level forecasting in mid-latitude storm-dominated and swell-mixed environments.
