High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach
Optimizing the Estimated Time of Arrival (ETA) for seaport-bound vessels is crucial to maritime operations since inaccurate ETA predictions can have a ripple effect, causing vessel schedule disruptions, congestion, and decreased port operational effectiveness. To address these challenges and fill su...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Maritime Transport Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666822X2500005X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850209260537905152 |
|---|---|
| author | Sunny Md. Saber Kya Zaw Thowai Muhammad Asifur Rahman Md. Mehedi Hassan A.B.M. Mainul Bari Asif Raihan |
| author_facet | Sunny Md. Saber Kya Zaw Thowai Muhammad Asifur Rahman Md. Mehedi Hassan A.B.M. Mainul Bari Asif Raihan |
| author_sort | Sunny Md. Saber |
| collection | DOAJ |
| description | Optimizing the Estimated Time of Arrival (ETA) for seaport-bound vessels is crucial to maritime operations since inaccurate ETA predictions can have a ripple effect, causing vessel schedule disruptions, congestion, and decreased port operational effectiveness. To address these challenges and fill substantial deficiencies in existing prediction models, we have introduced a novel hybrid tree-based stacking machine learning framework integrating Extra Trees, AutoGluon Tabular, and LightGBM, with Random Forest Regressor (RFR) as the meta-learner. Utilizing Automatic Identification System (AIS) data from vessels in the Baltic Sea, our model significantly improves ETA predictions, achieving a mean absolute percentage error (MAPE) of 0.25 %. Compared to existing machine learning algorithms, our stacking model exhibits superior prediction performance. Our study's feature importance analysis highlights the crucial role of variables like speed, distance, course, and vessel type in ETA forecasts. Cross-validation further confirms the robustness of our ensemble model. In conclusion, this study improves predictive analytics in marine logistics by giving useful information about real-time ETA estimates. This helps port authorities make the best use of their resources, reduces vessel idle time and congestion, and increases overall efficiency and sustainability. This way, this study can significantly contribute towards attaining operational excellence and provide a strong foundation for future predictive models, advancing smart port management and maritime logistics. |
| format | Article |
| id | doaj-art-91526833c2b24df89db656113fbe979c |
| institution | OA Journals |
| issn | 2666-822X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Maritime Transport Research |
| spelling | doaj-art-91526833c2b24df89db656113fbe979c2025-08-20T02:10:03ZengElsevierMaritime Transport Research2666-822X2025-06-01810013310.1016/j.martra.2025.100133High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approachSunny Md. Saber0Kya Zaw Thowai1Muhammad Asifur Rahman2Md. Mehedi Hassan3A.B.M. Mainul Bari4Asif Raihan5Department of Industrial and Production Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, BangladeshDepartment of Industrial and Production Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, BangladeshDepartment of Industrial and Production Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, BangladeshComputer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshDepartment of Industrial and Production Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh; Corresponding author.Institute of Forestry and Environmental Sciences, University of Chittagong, Chittagong 4331, BangladeshOptimizing the Estimated Time of Arrival (ETA) for seaport-bound vessels is crucial to maritime operations since inaccurate ETA predictions can have a ripple effect, causing vessel schedule disruptions, congestion, and decreased port operational effectiveness. To address these challenges and fill substantial deficiencies in existing prediction models, we have introduced a novel hybrid tree-based stacking machine learning framework integrating Extra Trees, AutoGluon Tabular, and LightGBM, with Random Forest Regressor (RFR) as the meta-learner. Utilizing Automatic Identification System (AIS) data from vessels in the Baltic Sea, our model significantly improves ETA predictions, achieving a mean absolute percentage error (MAPE) of 0.25 %. Compared to existing machine learning algorithms, our stacking model exhibits superior prediction performance. Our study's feature importance analysis highlights the crucial role of variables like speed, distance, course, and vessel type in ETA forecasts. Cross-validation further confirms the robustness of our ensemble model. In conclusion, this study improves predictive analytics in marine logistics by giving useful information about real-time ETA estimates. This helps port authorities make the best use of their resources, reduces vessel idle time and congestion, and increases overall efficiency and sustainability. This way, this study can significantly contribute towards attaining operational excellence and provide a strong foundation for future predictive models, advancing smart port management and maritime logistics.http://www.sciencedirect.com/science/article/pii/S2666822X2500005XEstimated time of arrivals (ETA) predictionMarine vesselsPort managementEnsemble methodMachine learning |
| spellingShingle | Sunny Md. Saber Kya Zaw Thowai Muhammad Asifur Rahman Md. Mehedi Hassan A.B.M. Mainul Bari Asif Raihan High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach Maritime Transport Research Estimated time of arrivals (ETA) prediction Marine vessels Port management Ensemble method Machine learning |
| title | High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach |
| title_full | High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach |
| title_fullStr | High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach |
| title_full_unstemmed | High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach |
| title_short | High-accuracy prediction of vessels’ estimated time of arrival in seaports: A hybrid machine learning approach |
| title_sort | high accuracy prediction of vessels estimated time of arrival in seaports a hybrid machine learning approach |
| topic | Estimated time of arrivals (ETA) prediction Marine vessels Port management Ensemble method Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2666822X2500005X |
| work_keys_str_mv | AT sunnymdsaber highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach AT kyazawthowai highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach AT muhammadasifurrahman highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach AT mdmehedihassan highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach AT abmmainulbari highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach AT asifraihan highaccuracypredictionofvesselsestimatedtimeofarrivalinseaportsahybridmachinelearningapproach |