Papers for

marine weather forecasters

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Deep learning models show limited gains for single-station wave height prediction

On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting

Abstract: 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.

Fri 25 SeptMachine Learning
The gist
Predicting how high waves will be is important for safety and planning. This study tested different deep learning models that use only past wave height data from one buoy to predict future wave heights. The models all performed similarly and only slightly better than just assuming the wave height stays the same. The results suggest that these models struggle to improve predictions with only single-station data, especially for extreme waves. The authors suggest future efforts should include weather data and separate wave types to get better forecasts.
Open → 2609.30688v1