EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Multimodal Intelligence Improves Maritime Congestion Forecasting and Port Optimization

Ziyang Shen, Hongrui Cai, Jonathan Pierce

Academic Journal of Management Science and Engineering · 2026

DOI: 10.62051/ajmse.v1n2.07 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Journal of Management Science and Engineering, 2026. Verfasst von Ziyang Shen und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maritime congestion at major global container ports represents one of the most pressing logistical bottlenecks of contemporary trade, with cascading consequences that permeate supply chains, freight economics, and carbon accounting simultaneously. This paper proposes a multimodal intelligence framework that integrates heterogeneous data streams — encompassing AIS positional records, meteorological observations, historical berth logs, and satellite-derived imagery — within a unified deep learning pipeline to forecast port congestion and optimize berth scheduling. A CNN-LSTM-GRU hybrid network with a cross-modal attention fusion layer is trained and evaluated on two-year real-world vessel traffic data from the Port of Shanghai and the Port of Singapore. Experimental results demonstrate that the proposed framework achieves a 23.7% reduction in MAE and a 19.4% reduction in RMSE relative to single-modality LSTM baselines. A downstream berth optimization module, driven by the congestion prediction output, reduces mean vessel waiting time by 17.6% under controlled simulation conditions. These findings confirm that multimodal data fusion constitutes a critical architectural principle for next-generation port intelligence systems.

Zitieren

APA

Shen, Z., Cai, H., & Pierce, J. (2026). Multimodal Intelligence Improves Maritime Congestion Forecasting and Port Optimization. Academic Journal of Management Science and Engineering. https://doi.org/10.62051/ajmse.v1n2.07

Vancouver

Shen Z, Cai H, Pierce J. Multimodal Intelligence Improves Maritime Congestion Forecasting and Port Optimization. Academic Journal of Management Science and Engineering. 2026. doi:10.62051/ajmse.v1n2.07

BibTeX
@article{Shen2026,
  author = {Shen, Ziyang and Cai, Hongrui and Pierce, Jonathan},
  title = {Multimodal Intelligence Improves Maritime Congestion Forecasting and Port Optimization},
  journal = {Academic Journal of Management Science and Engineering},
  year = {2026},
  doi = {10.62051/ajmse.v1n2.07}
}
Kostenlos starten →