Spatio-Temporal AIS Big Data Analytics of Vessel Traffic Patterns in Kaohsiung Port
DOI:
https://doi.org/10.59395/ijadis.v7i1.1504Keywords:
AIS Data Analytics , Vessel Traffic Patterns, Kaohsiung Port , Spatial Analysis , Maritime Traffic Management , Port OperationsAbstract
Maritime traffic management in major ports requires a comprehensive understanding of vessel movement patterns to ensure operational efficiency and safety. This study presents a spatio-temporal analysis of vessel traffic in Kaohsiung Port, Taiwan, utilizing a 10-month snapshot of AIS data (December 2024–October 2025). Employing quantitative methods including Kernel Density Estimation (KDE) for spatial intensity mapping, grid-based discretization for traffic density quantification, and temporal resolution analysis at multiple scales, the research identifies key operational hotspots and peak traffic periods. The analysis encompasses 1,247,890 AIS records from diverse vessel types, revealing distinct spatial clustering patterns in port entrance channels, anchorage zones, and terminal areas. Temporal analysis demonstrates pronounced diurnal and weekly cyclical patterns, with peak traffic intensities occurring during daytime operational hours and weekdays, reflecting commercial shipping schedules and port operational rhythms. The KDE-based hotspot identification reveals high-density zones concentrated within 0.5 nautical miles of major container terminals, indicating critical areas requiring enhanced traffic monitoring and collision avoidance measures. Grid-based traffic density quantification provides granular insights into vessel distribution across different port sectors, enabling zone-specific risk assessment and resource allocation strategies. The findings reveal complex spatio-temporal patterns that reflect the port's role as a major container hub in the Asia-Pacific region. Despite data quality limitations such as unspecified vessel types (59.9%) and incomplete destination fields, the results provide actionable insights for port authorities to enhance safety, optimize operations, and support strategic planning. This methodological framework demonstrates scalability and transferability to other port environments, contributing to the advancement of data-driven maritime traffic management systems
Downloads
References
[1] C.-C. Chou, C.-N. Wang, H.-P. Hsu, J.-F. Ding, W.-J. Tseng, and C.-Y. Yeh, Integrating AIS, GIS and E-Chart to Analyze the Shipping Traffic and Marine Accidents at the Kaohsiung Port, J. Mar. Sci. Eng., vol. 10, no. 10, 2022, doi: 10.3390/jmse10101543. DOI: https://doi.org/10.3390/jmse10101543
[2] T.-K. Liu, Y.-S. Chen, and Y.-T. Chen, Utilization of vessel automatic identification system (AIS) to estimate the emission of air pollutant from merchant vessels in the port of kaohsiung, Aerosol Air Qual. Res., vol. 19, no. 10, pp. 23412351, 2019, doi: 10.4209/aaqr.2019.07.0355. DOI: https://doi.org/10.4209/aaqr.2019.07.0355
[3] Z. Fang, H. Yu, R. Ke, S.-L. Shaw, and G. Peng, Automatic Identification System-Based Approach for Assessing the Near-Miss Collision Risk Dynamics of Ships in Ports, IEEE Trans. Intell. Transp. Syst., vol. 20, no. 2, pp. 534543, 2019, doi: 10.1109/TITS.2018.2816122. DOI: https://doi.org/10.1109/TITS.2018.2816122
[4] I. AbuAlhaol, R. Falcon, R. Abielmona, and E. Petriu, Mining Port Congestion Indicators from Big AIS Data, in 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro: IEEE, July 2018, pp. 18. doi: 10.1109/IJCNN.2018.8489187. DOI: https://doi.org/10.1109/IJCNN.2018.8489187
[5] D. Liu and G. Shi, Ship Collision Risk Assessment Based on Collision Detection Algorithm, IEEE Access, vol. 8, pp. 161969161980, 2020, doi: 10.1109/ACCESS.2020.3013957. DOI: https://doi.org/10.1109/ACCESS.2020.3013957
[6] G. Tang, Q. Cao, and X. Li, Analysis of vessel behaviors in costal waterways using big AIS data, in 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2019, 2019, pp. 290294. doi: 10.1109/ICCCBDA.2019.8725712. DOI: https://doi.org/10.1109/ICCCBDA.2019.8725712
[7] J. Yang, X. Bian, Y. Qi, X. Wang, Z. Yang, and J. Liu, A spatial-temporal data mining method for the extraction of vessel traffic patterns using AIS data, Ocean Eng., vol. 293, p. 116454, Feb. 2024, doi: 10.1016/j.oceaneng.2023.116454. DOI: https://doi.org/10.1016/j.oceaneng.2023.116454
[8] M.-C. Tsou, Online analysis process on Automatic Identification System data warehouse for application in vessel traffic service, Proc. Inst. Mech. Eng. Part M J. Eng. Marit. Environ., vol. 230, no. 1, pp. 199215, 2016, doi: 10.1177/1475090214541426. DOI: https://doi.org/10.1177/1475090214541426
[9] I.-L. Huang, M.-C. Lee, L. Chang, and J.-C. Huang, Development and Application of an Advanced Automatic Identification System (AIS)-Based Ship Trajectory Extraction Framework for Maritime Traffic Analysis, J. Mar. Sci. Eng., vol. 12, no. 9, p. 1672, Sept. 2024, doi: 10.3390/jmse12091672. DOI: https://doi.org/10.3390/jmse12091672
[10] Y. Li, Research on Multi-Port Ship Traffic Prediction Method Based on Spatiotemporal Graph Neural Networks, J. Mar. Sci. Eng., vol. 11, no. 7, 2023, doi: 10.3390/jmse11071379. DOI: https://doi.org/10.3390/jmse11071379
[11] H.-T. Lee, J.-S. Lee, H. Yang, and I.-S. Cho, An AIS data-driven approach to analyze the pattern of ship trajectories in ports using the DBSCAN algorithm, Appl. Sci. Switz., vol. 11, no. 2, pp. 133, 2021, doi: 10.3390/app11020799. DOI: https://doi.org/10.3390/app11020799
[12] Z. Liu, D. Zhou, Z. Zheng, Z. Wu, and L. Gang, An Analytic Model for Identifying Real-Time Anchorage Collision Risk Based on AIS Data, J. Mar. Sci. Eng., vol. 11, no. 8, p. 1553, Aug. 2023, doi: 10.3390/jmse11081553. DOI: https://doi.org/10.3390/jmse11081553
[13] J. Ma, Q. Hu, T. Liu, Z. Zhu, and Y. Zhou, Research on Ship Collision Risk Calculation in Port Navigation Waters Based on Ising Model and AIS Data, ASCE-ASME J. Risk Uncertain. Eng. Syst. Part Civ. Eng., vol. 10, no. 2, p. 04024003, June 2024, doi: 10.1061/AJRUA6.RUENG-1190. DOI: https://doi.org/10.1061/AJRUA6.RUENG-1190
[14] Rong Wen, Wenjing Yan, A. N. Zhang, Nguyen Quoc Chinh, and O. Akcan, Spatio-temporal route mining and visualization for busy waterways, in 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary: IEEE, Oct. 2016, pp. 000849000854. doi: 10.1109/SMC.2016.7844346. DOI: https://doi.org/10.1109/SMC.2016.7844346
[15] R. Wen and W. Yan, Vessel Crowd Movement Pattern Mining for Maritime Traffic Management, LOGI Sci. J. Transp. Logist., vol. 10, no. 2, pp. 105115, Nov. 2019, doi: 10.2478/logi-2019-0020. DOI: https://doi.org/10.2478/logi-2019-0020
[16] Chung-Yuan Nieh, Man-Chun Lee, Juan-Chen Huang, and Hsin-Chuan Kuo, RISK ASSESSMENT AND TRAFFIC BEHAVIOUR EVALUATION OF INBOUND SHIPS IN KEELUNG HARBOUR BASED ON AIS DATA, J. Mar. Sci. Technol., vol. 27, no. 4, Aug. 2019, doi: 10.6119/JMST.201908_27(4).0002.
[17] A. Nowy, K. azuga, L. Gucma, A. Androjna, M. Perkovi, and J. Sre, Modeling of Vessel Traffic Flow for Waterway DesignPort of winoujcie Case Study, Appl. Sci., vol. 11, no. 17, p. 8126, Sept. 2021, doi: 10.3390/app11178126. DOI: https://doi.org/10.3390/app11178126
[18] J. Ma, Y. Zhou, Y. Chang, Z. Zhu, G. Liu, and Z. Chen, TG-PGAT: An AIS Data-Driven Dynamic Spatiotemporal Prediction Model for Ship Traffic Flow in the Port, J. Mar. Sci. Eng., vol. 12, no. 10, p. 1875, Oct. 2024, doi: 10.3390/jmse12101875. DOI: https://doi.org/10.3390/jmse12101875
[19] M. Li, J. Mou, R. (Rachel) Liu, P. Chen, Z. Dong, and Y. He, Relational Model of Accidents and Vessel Traffic Using AIS Data and GIS: A Case Study of the Western Port of Shenzhen City, J. Mar. Sci. Eng., vol. 7, no. 6, p. 163, May 2019, doi: 10.3390/jmse7060163. DOI: https://doi.org/10.3390/jmse7060163
[20] F. Saransi and J. R. K. Bokau, Marine Traffic Risk Assessment Using Spatio-Temporal AIS Data in Makassar Port, Indonesia, in Proceedings of the 3rd International Conference and Maritime Development (ICMaD 2024), vol. 255, R. Mahmud, R. Rahimuddin, N. Amaliah, and A. Hayat, Eds., in Advances in Engineering Research, vol. 255. , Dordrecht: Atlantis Press International BV, 2024, pp. 7887. doi: 10.2991/978-94-6463-628-4_9. DOI: https://doi.org/10.2991/978-94-6463-628-4_9
[21] W. Wang et al., Ship Behavior Pattern Analysis Based on Multiship Encounter Detection, ASCE-ASME J. Risk Uncertain. Eng. Syst. Part Civ. Eng., vol. 10, no. 1, p. 04023045, Mar. 2024, doi: 10.1061/AJRUA6.RUENG-1145. DOI: https://doi.org/10.1061/AJRUA6.RUENG-1145
[22] M. Li, J. Mou, P. Chen, L. Chen, and P. Van Gelder, Real-Time Collision Risk Based Safety Management for Vessel Traffic in Busy Ports and Waterways, SSRN Electron. J., 2022, doi: 10.2139/ssrn.4238738. DOI: https://doi.org/10.2139/ssrn.4238738
[23] H. Park et al., AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting, 2025, arXiv. doi: 10.48550/ARXIV.2508.07668.
[24] L. Zhao and X. Fu, A novel index for real-time ship collision risk assessment based on velocity obstacle considering dimension data from AIS, Ocean Eng., vol. 240, p. 109913, Nov. 2021, doi: 10.1016/j.oceaneng.2021.109913. DOI: https://doi.org/10.1016/j.oceaneng.2021.109913
[25] B. Wang, Q. Tian, and W. Wang, Risk analysis of ship collision in complex waterway system based on AIS data, in 2022 3rd International Conference on Electronics, Communications and Information Technology (CECIT), Sanya, China: IEEE, Dec. 2022, pp. 176180. doi: 10.1109/CECIT58139.2022.00039. DOI: https://doi.org/10.1109/CECIT58139.2022.00039
[26] Y. Jiang, W. Xu, and D. Yang, Assessing the Credibility of AIS-Calculated Risks in Busy Waterways: A Case Study of Hong Kong Waters, Mathematics, vol. 13, no. 18, p. 2961, Sept. 2025, doi: 10.3390/math13182961. DOI: https://doi.org/10.3390/math13182961
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Afif Zuhri Arfianto, Anisa Fitri Santosa, Imam Sutrisno, Muhammad Khoirul Hasin, I Putu Sindhu Asmara, Dimas Pristovani Riananda, Dwi Sasmita Aji Pambudi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Share
Plum Analytics