Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jul 31;19(15):3363.
doi: 10.3390/s19153363.

Extracting Global Shipping Networks from Massive Historical Automatic Identification System Sensor Data: A Bottom-Up Approach

Zhihuan Wang  1 , Christophe Claramunt  2   3 , Yinhai Wang  4
Affiliations

Extracting Global Shipping Networks from Massive Historical Automatic Identification System Sensor Data: A Bottom-Up Approach

Zhihuan Wang et al. Sensors (Basel). .

Abstract

The increasing availability of big Automatic Identification Systems (AIS) sensor data offers great opportunities to track ship activities and mine spatial-temporal patterns of ship traffic worldwide. This research proposes a data integration approach to construct Global Shipping Networks (GSN) from massive historical ship AIS trajectories in a completely bottom-up way. First, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is applied to temporally identify relevant stop locations, such as marine terminals and their associated events. Second, the semantic meanings of these locations are obtained by mapping them to real ports as identified by the World Port Index (WPI). Stop events are leveraged to develop travel sequences of any ship between stop locations at multiple scales. Last, a GSN is constructed by considering stop locations as nodes and journeys between nodes as links. This approach generates different levels of shipping networks from the terminal, port, and country levels. It is illustrated by a case study that extracts country, port, and terminal level Global Container Shipping Networks (GCSN) from AIS trajectories of more than 4000 container ships in 2015. The main features of these GCSNs and the limitations of this work are finally discussed.

Keywords: AIS big data; DBSCAN; ship trajectory; shipping network; stay locations; stop events.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Bottom-up approach for Global Shipping Network (GSN) extraction: Datasets and principles.
Figure 2
Figure 2
A typical satellite imagery of a container terminal with large number of Automatic Identification Systems (AIS) data points reported from ships then stay at the terminal.
Figure 3
Figure 3
A bottom-up tree-based hierarchical structure of global ship stay locations with incoming AIS data at the bottom level. Global is at the top level, while the stops, terminals, ports, and countries are modelled at the middle levels.
Figure 4
Figure 4
Two different satellite images from terminal candidates. (a) Satellite image of a real container terminal. (b) Satellite image of a repairing shipyard.
Figure 5
Figure 5
Country-level network of a container ship with 11 nodes in 2015.
Figure 6
Figure 6
Port-level network of a container ship with 19 nodes located in 11 countries in 2015.
Figure 7
Figure 7
Terminal-level network of a container ship with 22 nodes located in 11 countries in 2015.
Figure 8
Figure 8
Global country-level container shipping network in 2015. A directed network with 2842 links and 150 countries. The size of a node refers the normalized betweenness centrality of a given node. The color refers to the four community clusters of the network. The color of a link is equal to the color of its departure node.
Figure 9
Figure 9
Port level Global Container Shipping Network (GCSN) extracted from ship AIS data in 2015. A directed and weighted network with 9227 links and 513 port nodes located in 150 countries. The size of a node refers the normalized betweenness centrality of a given node. The color refers to the five community clusters of the network. The color of a link is equal to the color of its departure node. The width of a link is equal to a rescaled link weight.
Figure 10
Figure 10
Terminal level GCSN extracted from ship AIS data in 2015. A directed and weighted network with 14,060 links and 754 container terminal nodes located in 513 ports. The size of a node refers the normalized betweenness centrality of a given node. The color refers to the six community clusters of the network. The color of a link is equal to the color of its departure node. The width of a link is equal to a rescaled link weight. The label of each node is the global terminal ID produced by this study.
See this image and copyright information in PMC

References

    1. Rodrigue J., Comtois C., Slack B. The Geography of Transport Systems. Routledge; New York, NY, USA: 2016.
    1. IMO . International Shipping and World Trade. International Maritime Organization; London, UK: 2006.
    1. Wang C., Wang J. Spatial pattern of the global shipping network and its hub-and-spoke system. Res. Transp. Econ. 2011;32:54–63. doi: 10.1016/j.retrec.2011.06.010. - DOI
    1. Viljoen N.M., Joubert J.W. The vulnerability of the global container shipping network to targeted link disruption. Phys. A Stat. Mech. Appl. 2016;462:396–409. doi: 10.1016/j.physa.2016.06.111. - DOI
    1. Peng P., Cheng S., Chen J., Liao M., Wu L., Liu X., Lu F. A fine-grained perspective on the robustness of global cargo ship transportation networks. J. Geogr. Sci. 2018;28:881–889. doi: 10.1007/s11442-018-1511-z. - DOI