Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enhancing Global Maritime Traffic Network Forecasting with Gravity-Inspired Deep Learning Models (2401.13098v3)

Published 23 Jan 2024 in cs.LG, cs.AI, cs.SI, and stat.AP

Abstract: Aquatic non-indigenous species (NIS) pose significant threats to biodiversity, disrupting ecosystems and inflicting substantial economic damages across agriculture, forestry, and fisheries. Due to the fast growth of global trade and transportation networks, NIS has been introduced and spread unintentionally in new environments. This study develops a new physics-informed model to forecast maritime shipping traffic between port regions worldwide. The predicted information provided by these models, in turn, is used as input for risk assessment of NIS spread through transportation networks to evaluate the capability of our solution. Inspired by the gravity model for international trades, our model considers various factors that influence the likelihood and impact of vessel activities, such as shipping flux density, distance between ports, trade flow, and centrality measures of transportation hubs. Accordingly, this paper introduces transformers to gravity models to rebuild the short- and long-term dependencies that make the risk analysis feasible. Thus, we introduce a physics-inspired framework that achieves an 89% binary accuracy for existing and non-existing trajectories and an 84.8% accuracy for the number of vessels flowing between key port areas, representing more than 10% improvement over the traditional deep-gravity model. Along these lines, this research contributes to a better understanding of NIS risk assessment. It allows policymakers, conservationists, and stakeholders to prioritize management actions by identifying high-risk invasion pathways. Besides, our model is versatile and can include new data sources, making it suitable for assessing international vessel traffic flow in a changing global landscape.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Group, S. R. Container shipping - statistics & facts. https://www.statista.com/topics/1367/container-shipping/#topicOverview (2022).
  2. Barry, S. C. et al. Ballast water risk assessment: Principles, processes, and methods. \JournalTitleICES Journal of Marine Science 65, 121–131, DOI: 10.1093/icesjms/fsn004 (2008).
  3. Initial risk assessment of alien species in nordic coastal waters (Nordic Council of Ministers, Copenhagen, Denmark, 1999).
  4. Ballast Water Risk Assessment: Port of Khark Island, Islamic Republic of Iran : Final Report. GloBallast Monograph Series (Programme Coordination Unit, Global Ballast Water Management Programme, 2003).
  5. Ballast Water Risk Assessment: Port of Saldanha Bay Republic of South Africa : November 2003 : Final Report. GloBallast Monograph Series (International Maritime Organization, 2004).
  6. Linking environmental conditions and ship movements to estimate invasive species transport across the global shipping network. \JournalTitleDiversity and Distributions 17, 93–102, DOI: 10.1111/j.1472-4642.2010.00696.x (2011).
  7. Risk assessment for exemptions from ballast water management – The Baltic Sea case study. \JournalTitleMarine Pollution Bulletin 75, 205–217, DOI: 10.1016/j.marpolbul.2013.07.031 (2013).
  8. Predicting the spread of marine species introduced by global shipping. \JournalTitleProceedings of the National Academy of Sciences 113, 5646–5651, DOI: 10.1073/pnas.1524427113 (2016).
  9. A temporal assessment of risk of non-indigenous species introduction by ballast water to Canadian coastal waters based on environmental similarity. \JournalTitleBiological Invasions 25, 1991–2005, DOI: 10.1007/s10530-023-03019-1 (2023).
  10. Saebi, M. et al. Higher-order patterns of aquatic species spread through the global shipping network. \JournalTitlePLOS ONE 15, 1–24, DOI: 10.1371/journal.pone.0220353 (2020).
  11. A decision support tool to prioritize ballast water compliance monitoring by ranking risk of non-indigenous species establishment. \JournalTitleJournal of Applied Ecology 58, 587–595, DOI: 10.1111/1365-2664.13822 (2021).
  12. The risk of marine bioinvasion caused by global shipping. \JournalTitleEcology Letters 16, 782–790, DOI: 10.1111/ele.12111 (2013).
  13. Developing an advanced information system to support ballast water management. \JournalTitleManagement of Biological Invasions 13, 68–80, DOI: 10.3391/mbi.2022.13.1.04 (2022).
  14. Center, S. E. R. National Ballast Information Clearinghouse (NBIC) Database. https://nbic.si.edu/database/. Accessed: 2023-09-30.
  15. The complex network of global cargo ship movements. \JournalTitleJournal of The Royal Society Interface 7, 1093–1103, DOI: 10.1098/rsif.2009.0495 (2010).
  16. A data augmentation algorithm for trajectory data. In 1st ACM SIGSPATIAL International Workshop on Methods for Enriched Mobility Data: Emerging issues and Ethical perspectives 2023 (EMODE ’23), 5, DOI: 10.1145/3615885.3628008 (ACM, New York, NY, USA, New York, NY, USA, 2023).
  17. Spadon, G. et al. Building a safer maritime environment through multi-path long-term vessel trajectory forecasting. \JournalTitlearXiv (2023). 2310.18948.
  18. Unfolding ais transmission behavior for vessel movement modeling on noisy data leveraging machine learning. \JournalTitleIEEE Access 11, 18821–18837, DOI: 10.1109/ACCESS.2022.3197215 (2023).
  19. Geotracknet - A maritime anomaly detector using probabilistic neural network representation of AIS tracks and A contrario detection. \JournalTitleIEEE Transactions on Intelligent Transportation Systems 23, 5655–5667, DOI: 10.1109/TITS.2021.3055614 (2022).
  20. TrAISformer-a generative transformer for AIS trajectory prediction. \JournalTitleCoRR abs/2109.03958 (2021). 2109.03958.
  21. A semi-supervised methodology for fishing activity detection using the geometry behind the trajectory of multiple vessels. \JournalTitleSensors 22, 6063, DOI: 10.3390/s22166063 (2022).
  22. Isaac Newton, I.Bernard Cohen & Anne Whitman. Proposition 75, Theorem 35. In The Principia: Mathematical Principles of Natural Philosophy, 3rd Edition (1726), 956 (University of California Press, 1999).
  23. Zipf, G. K. The P1 P2/D Hypothesis: On the Intercity Movement of Persons. \JournalTitleAmerican Sociological Review 11, 677–686, DOI: 10.2307/2087063 (1946).
  24. Gravity model in the Korean highway. \JournalTitleEurophysics Letters 81, 48005, DOI: 10.1209/0295-5075/81/48005 (2008).
  25. Modeling the effects of social distancing on the large-scale spreading of diseases. \JournalTitleEpidemics 38, 100544, DOI: https://doi.org/10.1016/j.epidem.2022.100544 (2022).
  26. Kramer, A. M. et al. Spatial spread of the west africa ebola epidemic. \JournalTitleRoyal Society Open Science 3, 160294, DOI: 10.1098/rsos.160294 (2016).
  27. The Gravity Model in International Trade: Advances and Applications (Cambridge University Press, 2010).
  28. Understanding individual human mobility patterns. \JournalTitleNature 453, 779–782, DOI: 10.1038/nature06958 (2008).
  29. Urban gravity in the global container shipping network. \JournalTitleJournal of Transport Geography 85, 102729, DOI: 10.1016/j.jtrangeo.2020.102729 (2020).
  30. Gravity models do not explain, and cannot predict, international migration dynamics. \JournalTitleHumanities and Social Sciences Communications 9, 1–10, DOI: 10.1057/s41599-022-01067-x (2022).
  31. Limits of Predictability in Human Mobility. \JournalTitleScience 327, 1018–1021, DOI: 10.1126/science.1177170 (2010).
  32. A universal model for mobility and migration patterns. \JournalTitleNature 484, 96–100, DOI: 10.1038/nature10856 (2012).
  33. Gravity versus radiation models: On the importance of scale and heterogeneity in commuting flows. \JournalTitlePhysical Review E: Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics 88, 022812, DOI: 10.1103/PhysRevE.88.022812 (2013).
  34. Predicting commuter flows in spatial networks using a radiation model based on temporal ranges. \JournalTitleNature Communications 5, 5347, DOI: 10.1038/ncomms6347 (2014).
  35. Mazzoli, M. et al. Field theory for recurrent mobility. \JournalTitleNature Communications 10, 3895, DOI: 10.1038/s41467-019-11841-2 (2019).
  36. Traffic Flow Prediction Based on Spatiotemporal Potential Energy Fields. \JournalTitleIEEE Transactions on Knowledge and Data Engineering 1–14, DOI: 10.1109/TKDE.2022.3221183 (2022).
  37. Patient trajectory prediction in the Mimic-III dataset, challenges and pitfalls. \JournalTitleCoRR abs/1909.04605 (2019). 1909.04605.
  38. Lig-doctor: Efficient patient trajectory prediction using bidirectional minimal gated-recurrent networks. \JournalTitleInformation Sciences 545, 813–827, DOI: 10.1016/j.ins.2020.09.024 (2021).
  39. Spadon, G. et al. Pay attention to evolution: Time series forecasting with deep graph-evolution learning. \JournalTitleIEEE Transactions on Pattern Analysis and Machine Intelligence 44, 5368–5384, DOI: 10.1109/TPAMI.2021.3076155 (2022).
  40. Brandoli, B. et al. Aircraft fuselage corrosion detection using artificial intelligence. \JournalTitleSensors 21, DOI: 10.3390/s21124026 (2021).
  41. A Deep Gravity model for mobility flows generation. \JournalTitleNature Communications 12, 6576, DOI: 10.1038/s41467-021-26752-4 (2021).
  42. Reconstructing commuters network using machine learning and urban indicators. \JournalTitleScientific reports 9, 11801, DOI: 10.1038/s41598-019-48295-x (2019).
  43. The Growth Lab at Harvard University. International trade data (SITC, rev. 2), DOI: 10.7910/DVN/H8SFD2 (2019).
  44. Vaswani, A. et al. Attention is all you need. In Guyon, I. et al. (eds.) Advances in Neural Information Processing Systems, vol. 30 (Curran Associates, Inc., 2017).
  45. Carlini, E. et al. Understanding evolution of maritime networks from automatic identification system data. \JournalTitleGeoInformatica 26, 479–503, DOI: 10.1007/s10707-021-00451-0 (2022).
  46. National Geospatial-Intelligence Agency (NGA). World Port Index (Pub 150). https://msi.nga.mil/Publications/WPI (2019).
  47. The PageRank Citation Ranking : Bringing Order to the Web. In The Web Conference (1999). https://www.eecs.harvard.edu/~michaelm/CS222/pagerank.pdf.
  48. Gent Halili. Searoute-py: A python package to calculate the shortest sea route between two points on Earth. https://github.com/genthalili/searoute-py (2022).
  49. Centrality measures in spatial networks of urban streets. \JournalTitlePhys. Rev. E 73, 036125, DOI: 10.1103/PhysRevE.73.036125 (2006).
  50. Shipping network design in a growth market: The case of Indonesia. \JournalTitleSpecial Issue on China’s Belt and Road Initiative 117, 108–125, DOI: 10.1016/j.tre.2017.10.001 (2018).
  51. Codes for the representation of names of countries and their subdivisions - Part 2: Country subdivision code. Standard, International Organization for Standardization, Geneva, Switzerland (2020). https://www.iso.org/standard/72483.html.
  52. A Survey on Deep Learning for Human Mobility. \JournalTitleACM Computing Surveys 55, 7:1–7:44, DOI: 10.1145/3485125 (2021).
  53. Systematic comparison of trip distribution laws and models. \JournalTitleJournal of Transport Geography 51, 158–169, DOI: 10.1016/j.jtrangeo.2015.12.008 (2016).
  54. Barbosa, H. et al. Human mobility: Models and applications. \JournalTitlePhysics Reports 734, 1–74, DOI: 10.1016/j.physrep.2018.01.001 (2018).
  55. Global port environmental data used for environmental distance calculations [Dataset], DOI: 10.5061/dryad.69p8cz906 (2020).
  56. Introduction To Algorithms (MIT Press, 2001).
  57. Konstantopoulos, T. Introduction to projective geometry. September (Dover Publications, 2012).
  58. Van Steen, M. Graph Theory and Complex Networks: An Introduction (Maarten van Steen, 2010).
  59. Incremental Closeness Centrality for Dynamically Changing Social Networks. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining - ASONAM’13, DOI: 10.1145/2492517.2500270 (Association for Computing Machinery (ACM), 2013).
  60. Efficiency of informational transfer in regular and complex networks. \JournalTitlePhysical Review E - Statistical, Nonlinear, and Soft Matter Physics 71, 036122, DOI: 10.1103/PhysRevE.71.036122 (2005).
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets