Scholarlink

This paper presents a machine learning-based approach to predicting vessel arrival times and optimizing berth allocation, two critical challenges in maritime logistics. Accurate predictions are vital for efficient port operations, minimizing congestion and reducing logistical strain on supply chain stakeholders. Using historical AIS data from the Norwegian Base Station and satellite observations (August 1-September 24, 2024), three regression models—Gradient Boosting, K-Nearest Neighbors (KNN), and Random Forest—were evaluated. Random Forest achieved the best performance, with an \(R^2\) of 0.704 and a MAPE of 0.0285%, demonstrating superior predictive power. These results highlight the potential of machine learning to enhance berth scheduling and overall port efficiency.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting Vessel Arrival Time Using Machine Learning for Enhanced Port Efficiency and Optimal Berth Allocation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anfal Albloushi,
  • Ioannis Karamitsos,
  • Andreas Kanavos,
  • Sanjay Modak

摘要

This paper presents a machine learning-based approach to predicting vessel arrival times and optimizing berth allocation, two critical challenges in maritime logistics. Accurate predictions are vital for efficient port operations, minimizing congestion and reducing logistical strain on supply chain stakeholders. Using historical AIS data from the Norwegian Base Station and satellite observations (August 1-September 24, 2024), three regression models—Gradient Boosting, K-Nearest Neighbors (KNN), and Random Forest—were evaluated. Random Forest achieved the best performance, with an \(R^2\) of 0.704 and a MAPE of 0.0285%, demonstrating superior predictive power. These results highlight the potential of machine learning to enhance berth scheduling and overall port efficiency.