{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:46:15Z","timestamp":1760060775626,"version":"build-2065373602"},"reference-count":44,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["957237","101135826"],"award-info":[{"award-number":["957237","101135826"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Maritime safety, environmental protection, and efficient traffic management increasingly rely on data-driven technologies. However, leveraging Automatic Identification System (AIS) data for predictive modelling faces two major challenges: the massive volume of data generated in real-time and growing privacy concerns associated with proprietary vessel information. This paper proposes a novel, privacy-preserving framework for vessel traffic density (VTD) prediction that addresses both challenges. The approach combines the European Maritime Observation and Data Network\u2019s (EMODNet) grid-based VTD calculation method with Convolutional Neural Networks (CNN) to model spatiotemporal traffic patterns and employs Federated Learning to collaboratively build a global predictive model without the need for explicit sharing of proprietary AIS data. Three geographically diverse AIS datasets were harmonized, processed, and used to train local CNN models on hourly VTD matrices. These models were then aggregated via a Federated Learning framework under a lifelong learning scenario. Evaluation using Sparse Mean Squared Error shows that the federated global model achieves promising accuracy in sparse data scenarios and maintains performance parity when compared with local CNN-based models, all while preserving data privacy and minimizing hardware performance needs and data communication overheads. The results highlight the approach\u2019s effectiveness and scalability for real-world maritime applications in traffic forecasting, safety, and operational planning.<\/jats:p>","DOI":"10.3390\/ijgi14090359","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T12:24:25Z","timestamp":1758198265000},"page":"359","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vessel Traffic Density Prediction: A Federated Learning Approach"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2700-5384","authenticated-orcid":false,"given":"Amin","family":"Khodamoradi","sequence":"first","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6068-1982","authenticated-orcid":false,"given":"Paulo Alves","family":"Figueiras","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5168-4786","authenticated-orcid":false,"given":"Andr\u00e9","family":"Grilo","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"given":"Luis","family":"Louren\u00e7o","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"given":"Bruno","family":"R\u00eaga","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2884-776X","authenticated-orcid":false,"given":"Carlos","family":"Agostinho","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-1840","authenticated-orcid":false,"given":"Ruben","family":"Costa","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3703-6854","authenticated-orcid":false,"given":"Ricardo","family":"Jardim-Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"UNINOVA\u2014Centre of Technology and Systems (CTS), FCT Campus, 2829-516 Caparica, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"ref_1","unstructured":"Lavery, B. (2022). A Short History of Seafaring, Dorling Kindersley Ltd."},{"key":"ref_2","unstructured":"United Nations Conference on Trade and Development (2024). Review of Maritime Transport 2024: Navigating Maritime Chokepoints, United Nations."},{"key":"ref_3","unstructured":"European Maritime Safety Agency (2024). Annual Overview of Marine Casualties and Incidents 2024, European Union."},{"key":"ref_4","unstructured":"Transportation Safety Board of Canada (2020). Statistical Summary: Marine Transportation Occurrences in 2020, Government of Canada."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1080\/03088839.2020.1788731","article-title":"Big Data and Artificial Intelligence in the Maritime Industry: A Bibliometric Review and Future Research Directions","volume":"47","author":"Munim","year":"2020","journal-title":"Marit. Policy Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"120879","DOI":"10.1016\/j.techfore.2021.120879","article-title":"Digital Tansformation in the Mritime Tansport Sctor","volume":"170","author":"Tijan","year":"2021","journal-title":"Technol. Forecast. Soc. Change"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"114975","DOI":"10.1016\/j.eswa.2021.114975","article-title":"The Promises and Perils of Automatic Identification System Data","volume":"178","author":"Emmens","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sun, J., Yi, Z., Zhuang, Z., and Jiang, S. (2025). Securing Automatic Identification System Communications Using Physical-Layer Key Generation Protocol. J. Mar. Sci. Eng., 13.","DOI":"10.3390\/jmse13020386"},{"key":"ref_9","unstructured":"Falco, L., Pititto, A., Adnams, W., Earwaker, N., and Greidanus, H. (2019). EU Vessel Density Map Detailed Method, European Marine Observation and Data Network (EMODNet). Available online: https:\/\/emodnet-humanactivities.eu\/documents\/Vessel%20density%20maps_method_v1.5.pdf."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, M., Li, B., Qi, Z., Li, J., and Wu, J. (2024). Enhancing Maritime Navigational Safety: Ship Trajectory Prediction Using ACoAtt\u2013LSTM and AIS Data. ISPRS Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13030085"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Abreha, H.G., Hayajneh, M., and Serhani, M.A. (2022). Federated Learning in Edge Computing: A Systematic Survey. Sensors, 22.","DOI":"10.3390\/s22020450"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1017\/S0373463316000345","article-title":"Mapping Global Shipping Density from AIS Data","volume":"70","author":"Wu","year":"2017","journal-title":"J. Navig."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.visinf.2021.10.002","article-title":"Visualization and Visual Analysis of Vessel Trajectory Data: A Survey","volume":"5","author":"Liu","year":"2021","journal-title":"Vis. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1017\/S0373463313000519","article-title":"Use of AIS Data to Characterise Marine Traffic Patterns and Ship Collision Risk off the Coast of Portugal","volume":"66","author":"Silveira","year":"2013","journal-title":"J. Navig."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"022032","DOI":"10.1088\/1755-1315\/310\/2\/022032","article-title":"Shipping Density Assessment Based on Trajectory Big Data","volume":"310","author":"Dai","year":"2019","journal-title":"IOP Conf. Ser. Earth Environ. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Aguilar, G.D., Tirol, Y.P., Basina, R.M., and Alcedo, J. (2025). Spatial Analysis of Maritime Disasters in the Philippines: Distribution Patterns and Identification of High-Risk Areas. Int. J. Geo-Inf., 14.","DOI":"10.3390\/ijgi14010031"},{"key":"ref_17","unstructured":"Lee, S. (2025, March 13). A Comprehensive Guide to Kernel Density Estimation with Python Implementation. Number Analytics\u2014Blog. Available online: https:\/\/www.numberanalytics.com\/blog\/comprehensive-guide-kernel-density-estimation-python."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xiao, G., Yang, D., Xu, L., Li, J., and Jiang, Z. (2024). The Application of Artificial Intelligence Technology in Shipping: A Bibliometric Review. J. Mar. Sci. Eng., 12.","DOI":"10.3390\/jmse12040624"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, D., and Liu, R.W. (2024). Application of Artificial Intelligence in Maritime Transportation. J. Mar. Sci. Eng., 12.","DOI":"10.3390\/books978-3-7258-0656-0"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103426","DOI":"10.1016\/j.tre.2024.103426","article-title":"Harnessing the Power of Machine Learning for AIS Data-Driven Maritime Research: A Comprehensive Review","volume":"183","author":"Yang","year":"2024","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, W., Xiong, W., Ouyang, X., and Chen, L. (2024). TPTrans: Vessel Trajectory Prediction Model Based on Transformer Using AIS Data. Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13110400"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107463","DOI":"10.1016\/j.ress.2021.107463","article-title":"Spatial Correlation Analysis of Near Ship Collision Hotspots with Local Maritime Traffic Characteristics","volume":"209","author":"Rong","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"117605","DOI":"10.1016\/j.oceaneng.2024.117605","article-title":"Multi-ship Encounter Situation Graph Structure Learning for Ship Collision Avoidance based on AIS Big Data with Spatio-temporal Edge and Node Attention Graph Convolutional Networks","volume":"301","author":"Gao","year":"2024","journal-title":"Ocean Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lee, E., Khan, J., Son, W.-J., and Kim, K. (2023). An Efficient Feature Augmentation and LSTM-Based Method to Predict Maritime Traffic Conditions. Appl. Sci., 13.","DOI":"10.3390\/app13042556"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108696","DOI":"10.1016\/j.engappai.2024.108696","article-title":"A Data Mining-then-predict Method for Proactive Maritime Traffic Management by Machine Learning","volume":"135","author":"Liu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Graser, A., Weissenfeld, A., Heistracher, C., Dragaschnig, M., and Widhalm, P. (2024, January 24\u201327). Federated Learning for Anomaly Detection in Maritime Movement Data. Proceedings of the 25th IEEE International Conference on Mobile Data Management (MDM), Brussels, Belgium.","DOI":"10.1109\/MDM61037.2024.00030"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tritsarolis, A., Pelekis, N., Bereta, K., Zissis, D., and Theodoridis, Y. (2024, January 24\u201327). On Vessel Location Forecasting and the Effect of Federated Learning. Proceedings of the 25th IEEE International Conference on Mobile Data Management (MDM), Brussels, Belgium.","DOI":"10.1109\/MDM61037.2024.00031"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"117668","DOI":"10.1016\/j.oceaneng.2024.117668","article-title":"A Novel Prediction Model for Ship Fuel Consumption Considering Shipping Data Privacy: An XGBoost-IGWO-LSTM-based Personalized Federated Learning Approach","volume":"302","author":"Han","year":"2024","journal-title":"Ocean Eng."},{"key":"ref_29","unstructured":"(2012, June 14). Chorochronos.org. AIS Brest, France. Available online: https:\/\/chorochronos.datastories.org\/?q=node\/9."},{"key":"ref_30","unstructured":"Norwegian Coastal Administration (2025, March 13). Automatic Identification System (AIS). Kystverket. Available online: https:\/\/kystverket.no\/en\/navigation-and-monitoring\/ais\/."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"107782","DOI":"10.1016\/j.dib.2021.107782","article-title":"The Piraeus AIS dataset for large-scale maritime data analytics","volume":"40","author":"Tritsarolis","year":"2022","journal-title":"Data Brief"},{"key":"ref_32","unstructured":"European Commission (2021, January 01). VesselAI Project\u2014Enabling Maritime Digitalisation by Extreme-Scale Analytics, AI and Digital Twins (Grant Agreement ID: 957237). Available online: https:\/\/cordis.europa.eu\/project\/id\/957237."},{"key":"ref_33","unstructured":"PostGreSQL Global Development Group (2025, May 08). PostgreSQL: The World\u2019s Most Advanced Open Source Relational Database. Available online: https:\/\/www.postgresql.org\/."},{"key":"ref_34","unstructured":"PostGIS Project Steering Committee (2025, May 16). PostGIS. PostGIS PSC & OSGeo. Available online: https:\/\/postgis.net\/."},{"key":"ref_35","unstructured":"Chollet, F. (2015, March 27). Keras: Deep Leraning for Humans. Keras Team. Available online: https:\/\/keras.io\/."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., and Yu, H. (2020). Horizontal Federated Learning. Federated Learning\u2014Synthesis Lectures on Artificial Intelligence and Machine Learning, Springer.","DOI":"10.1007\/978-3-031-01585-4"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1016\/j.procs.2025.03.232","article-title":"A Comprehensive Review of Open-Source Federated Learning Frameworks","volume":"260","author":"Mehdi","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_38","unstructured":"Beutel, D.J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K.H., Parcollet, T., and de Gusm\u00e3o, P.P.B. (2020). Flower: A Friendly Federated AI Framework. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lewis, K., Rost, N.S., Guttag, J., and Dalca, A.V. (2020, January 2\u20134). Fast Learning-based Registration of Sparse 3D Clinical Images. Proceedings of the 2020 ACM Conference on Health, Inference, and Learning, Toronto, ON, Canada.","DOI":"10.1145\/3368555.3384462"},{"key":"ref_40","unstructured":"Finn, C., Goodfellow, I., and Levine, S. (2016, January 5\u201310). Unsupervised Learning for Physical Interaction Through Video Prediction. Proceedings of the Advances in Neural Information Processing Systems 29 (NIPS 2016), Barcelona, Spain."},{"key":"ref_41","unstructured":"Joshi, A. (2021, June 02). Next-Frame Video Prediction with Convolutional LSTMs. Keras. Available online: https:\/\/keras.io\/examples\/vision\/conv_lstm\/."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R.A., Tang, X., Liu, Y., and Agarwala, A. (2017, January 22\u201329). Video Frame Synthesis Using Deep Voxel Flow. Proceedings of the IEEE International Conference on Computer Vision (ICCV 2017), Venice, Italy.","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref_43","unstructured":"Apache Software Foundation (2021, June 02). Apache Superset. Available online: https:\/\/superset.apache.org\/."},{"key":"ref_44","unstructured":"European Commission (2024, January 01). AI-DAPT: AI-Ops Framework for Automated, Intelligent and Reliable Data\/AI Pipelines Lifecycle with Humans-in-the-Loop and Coupling of Hybrid Science-Guided and AI Models. Available online: https:\/\/cordis.europa.eu\/project\/id\/101135826."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/359\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:53Z","timestamp":1760035673000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":44,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["ijgi14090359"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14090359","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,9,18]]}}}