Variable-Wise Attention for One-Hour-Ahead Forecasting of Moored-Vessel Motions with Vessel-Holdout Evaluation
Journal of Marine Science and Engineering · 19.11.2026 · 14 (22) · 2198
DOI: 10.3390/jmse14222198 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 19.11.2026. Verfasst von Xiaochi Cai und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Forecasts of moored-vessel motion help port operators identify safe operating windows, yet same-vessel training may overstate performance on unseen ships. We evaluate a variable-wise inverted transformer for one-hour-ahead prediction of significant motion amplitudes in all six degrees of freedom, using motion history, ocean-meteorological forcing, vessel geometry, and berthing information. The public dataset from the Outer Port of Punta Langosteira uniquely combines hourly amplitudes, concurrent forcing, vessel particulars, and a vessel-level partition; 81 vessels are used for development and 3 were held out for testing. Against persistence, linear regression, LSTM, DLinear, PatchTST, and a quasi-static baseline, the transformer attains the lowest mean absolute error for sway (0.063 m) and pitch (0.018°), while linear regression is best for roll and yaw; surge and heave (six windows each) are reported as case-specific observations. Among the four adequately sampled responses, the transformer ranks first in normalized mean absolute error (0.169), narrowly ahead of linear regression and persistence; the improvement is statistically supported for sway (p=0.035) but not for pitch (p=0.365). Error grows with lead time and wave height, CPU latency remains below 0.1 ms per window, and Monte Carlo dropout intervals are under-calibrated. Variable-wise attention offers a lightweight option on par with the strongest baselines, underscoring the strength of simple baselines and the importance of vessel-level holdout evaluation.
Zitieren
APA
Cai, X., Yao, W., Jia, Z., Zhao, L., & Wen, S. (2026). Variable-Wise Attention for One-Hour-Ahead Forecasting of Moored-Vessel Motions with Vessel-Holdout Evaluation. Journal of Marine Science and Engineering, 14(22), 2198. https://doi.org/10.3390/jmse14222198
Vancouver
Cai X, Yao W, Jia Z, Zhao L, Wen S. Variable-Wise Attention for One-Hour-Ahead Forecasting of Moored-Vessel Motions with Vessel-Holdout Evaluation. Journal of Marine Science and Engineering. 2026;14(22):2198. doi:10.3390/jmse14222198
BibTeX
@article{Cai2026,
author = {Cai, Xiaochi and Yao, Wen and Jia, Zilu and Zhao, Lingxiao and Wen, Shuli},
title = {Variable-Wise Attention for One-Hour-Ahead Forecasting of Moored-Vessel Motions with Vessel-Holdout Evaluation},
journal = {Journal of Marine Science and Engineering},
year = {2026},
volume = {14},
number = {22},
pages = {2198},
doi = {10.3390/jmse14222198}
}
EUVIMED