EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of a Reinforcement Learning-Based Ship Voyage Planning Optimization Method Applying Machine Learning-Based Berth Dwell-Time Prediction as a Time Constraint

Youngseo Park, Suhwan Kim, Jeongon Eom, Sewon Kim

Journal of Marine Science and Engineering · 25.12.2025 · 14 (1) · 43

DOI: 10.3390/jmse14010043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 25.12.2025. Verfasst von Youngseo Park und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Oceans and Fisheries, Ministry of Education, Ministry of Science and ICT (MSIT), Republic of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Global container shipping faces increasing pressure to reduce fuel consumption and greenhouse gas (GHG) emissions while still meeting strict port schedules under highly uncertain terminal operations and met-ocean conditions. However, most existing voyage-planning approaches either ignore real port operation variability or treat fuel optimization and just-in-time (JIT) arrival as separate problems, limiting their applicability in actual operations. This study presents a data-driven just-in-time voyage optimization framework that integrates port-side uncertainty and marine environmental dynamics into the routing process. A dwell-time prediction model based on Gradient Boosting was developed using port throughput and meteorological–oceanographic variables, achieving a validation accuracy of R2 = 0.84 and providing a data-driven required time of arrival (RTA) estimate. A Transformer encoder model was constructed to forecast fuel consumption from multivariate navigation and environmental data, and the model achieved a segment-level predictive performance with an R2 value of approximately 0.99. These predictive modules were embedded into a Deep Q-Network (DQN) routing model capable of optimizing headings and speed profiles under spatially varying ocean conditions. Experiments were conducted on three container-carrier routes in which the historical AIS trajectories served as operational benchmark routes. Compared with these AIS-based baselines, the optimized routes reduced fuel consumption and CO2 emissions by approximately 26% to 69%, while driving the JIT arrival deviation close to zero. The proposed framework provides a unified approach that links port operations, fuel dynamics, and ocean-aware route planning, offering practical benefits for smart and autonomous ship navigation.

Förderung

  • Ministry of Oceans and Fisheries
  • Ministry of Education
  • Ministry of Science and ICT (MSIT), Republic of Korea
  • Ministry of Trade, Industry & Energy

Zitieren

APA

Park, Y., Kim, S., Eom, J., & Kim, S. (2025). Development of a Reinforcement Learning-Based Ship Voyage Planning Optimization Method Applying Machine Learning-Based Berth Dwell-Time Prediction as a Time Constraint. Journal of Marine Science and Engineering, 14(1), 43. https://doi.org/10.3390/jmse14010043

Vancouver

Park Y, Kim S, Eom J, Kim S. Development of a Reinforcement Learning-Based Ship Voyage Planning Optimization Method Applying Machine Learning-Based Berth Dwell-Time Prediction as a Time Constraint. Journal of Marine Science and Engineering. 2025;14(1):43. doi:10.3390/jmse14010043

BibTeX
@article{Park2025,
  author = {Park, Youngseo and Kim, Suhwan and Eom, Jeongon and Kim, Sewon},
  title = {Development of a Reinforcement Learning-Based Ship Voyage Planning Optimization Method Applying Machine Learning-Based Berth Dwell-Time Prediction as a Time Constraint},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {14},
  number = {1},
  pages = {43},
  doi = {10.3390/jmse14010043}
}
Kostenlos starten →