EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Prediction of Ship Roll Motion with Monte Carlo Dropout

Gi-yong Kim, Chaeog Lim, Sang-jin Oh, In-hyuk Nam, Yu-mi Lee, Sung-chul Shin

Journal of Marine Science and Engineering · 15.12.2025 · 13 (12) · 2378

DOI: 10.3390/jmse13122378 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 15.12.2025. Verfasst von Gi-yong Kim und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Oceans and Fisheries, Korea Institute of Energy Technology Evaluation and Planning.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of ship roll motion is essential for safe and autonomous navigation. This study presents a deep learning framework that estimates both roll motion and epistemic uncertainty using Monte Carlo (MC) Dropout. Two architectures, a Long Short-Term Memory (LSTM) network and a Transformer encoder, were trained on HydroD–Wasim simulations covering various sea states, speeds, and damage conditions, and validated with real voyage data from two ferries, showing complementary performance, where LSTM achieved higher accuracy and Transformer provided more reliable confidence intervals. Model performance was evaluated by mean squared error (MSE), prediction interval coverage probability (PICP), and prediction interval normalized average width (PINAW). The LSTM achieved lower MSE, showing superior deterministic accuracy, while the Transformer produced higher PICP and wider PINAW, indicating more reliable uncertainty estimation. Results confirm that MC Dropout effectively quantifies epistemic uncertainty, improving the reliability of deep learning–based ship motion forecasting for intelligent maritime operations.

Förderung

  • Ministry of Oceans and Fisheries
  • Korea Institute of Energy Technology Evaluation and Planning

Zitieren

APA

Kim, G., Lim, C., Oh, S., Nam, I., Lee, Y., & Shin, S. (2025). Deep Learning-Based Prediction of Ship Roll Motion with Monte Carlo Dropout. Journal of Marine Science and Engineering, 13(12), 2378. https://doi.org/10.3390/jmse13122378

Vancouver

Kim G, Lim C, Oh S, Nam I, Lee Y, Shin S. Deep Learning-Based Prediction of Ship Roll Motion with Monte Carlo Dropout. Journal of Marine Science and Engineering. 2025;13(12):2378. doi:10.3390/jmse13122378

BibTeX
@article{Kim2025,
  author = {Kim, Gi-yong and Lim, Chaeog and Oh, Sang-jin and Nam, In-hyuk and Lee, Yu-mi and Shin, Sung-chul},
  title = {Deep Learning-Based Prediction of Ship Roll Motion with Monte Carlo Dropout},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {13},
  number = {12},
  pages = {2378},
  doi = {10.3390/jmse13122378}
}
Kostenlos starten →