{"id":793,"date":"2021-03-21T18:06:52","date_gmt":"2021-03-21T18:06:52","guid":{"rendered":"https:\/\/localhost\/monitraffic\/?page_id=793"},"modified":"2023-11-10T14:18:17","modified_gmt":"2023-11-10T14:18:17","slug":"task-2","status":"publish","type":"page","link":"https:\/\/monitraffic.tecnico.ulisboa.pt\/?page_id=793","title":{"rendered":"Task 2"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t
<\/div>\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

Task 2<\/h1>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

Characterisation of maritime traffic and safe routes for ships<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t

A data-driven approach for maritime traffic network extraction based on Automatic Identification System (AIS) data has been proposed. A maritime traffic network, consisting of nodes that represent waypoint areas and navigational legs, is constructed to represent maritime traffic at a larger scale. The proposed maritime traffic network extraction approach consists of three phases:<\/p>

  1. Extraction of maritime traffic motion patterns based on historical Automatic Identification System data;<\/li>
  2. Enriching the ship trajectories with semantic information and each ship trajectory is abstracted as an \u201corigin-waypoint-destination\u201d itinerary object;<\/li>
  3. Ship itinerary objects are further merged into nodes and edges of a directed maritime traffic network.<\/li><\/ol>

    Then, a data mining approach is proposed for the probabilistic characterization of the maritime traffic off the continental coast of Portugal based on Automatic Identification System data that combines trajectory compression and clustering algorithms to characterise routes as a set of straight legs and connecting turning sections.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tMaritime traffic Network extraction<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

    A maritime traffic route extraction and modelling method based on historical AIS data is proposed to identify and understand the maritime traffic patterns. The extraction of maritime traffic routes consists of grouping ship trajectories that follow the same itinerary, e.g., from traffic origin areas to destination areas. The ship static positions and enter\/exit points are clustered using the OPTICS algorithm. Differently from centroid-based clustering, the OPTICS algorithm does not require the number of clusters to be defined in advance. Instead, arbitrarily shaped clusters can be determined as often observed in maritime traffic context. Once the clusters are learned, individual ship trajectories are grouped into traffic-groups, which are defined as sets of ship trajectories corresponding to different departure or arrival areas. In this study, 68 traffic-groups are detected, as shown in Figure 1.<\/p>\n

    \n
    \n \"Traffic-group\n
    \n Figure 1 – Traffic-group defined by departure-arrival areas and ship route model based on the AIS data<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n

    By taking the traffic origin-destination areas as nodes and the extracted ship routes as edges, a maritime traffic abstraction network model is formed. Maritime domain knowledge can add semantic information to the maritime traffic abstraction model and enhance the interpretation of ship movements, which potentially can improve the maritime traffic management. The geographical domain knowledge comes in the form of two simple ontologies. One ontology has definitions of the ports of Portugal, the polygons and names that define the different ports follow the GeoNames ontology. The other ontology consists of the Traffic Separation Schemes (TSS) off the Portuguese coast, off Cape Roca and off Cape San Vincent. The resulting maritime traffic abstraction of the study area can be represented by the network model shown in Figure 2.<\/p>\n\n

    \n
    \n \"Maritime\n
    \n Figure 2 – Maritime traffic network abstraction off the coast of Portugal<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tMaritime traffic route characterisation<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t
    An approach for the probabilistic characterisation of shipping routes based on historical AIS data has been proposed. The analysis of traffic patterns is essential as it provides the possibility to integrate and enrich maritime traffic services including route modelling, trajectory prediction and detection of abnormal traffic behaviour. Figure 3 shows the flowchart of the proposed approach for probabilistic characterisation of ship routes that consist of three main steps:\n
      \n \t
    1. Definition of traffic patterns by grouping ship trajectories according to final destinations;<\/li>\n \t
    2. Waypoints and route legs identification;<\/li>\n \t
    3. Probabilistic characterization of ship trajectory at waypoints and route legs.<\/li>\n<\/ol>\n\n

      \n
      \n \"Flowchart\n
      \n Figure 3 – Flowchart of maritime traffic route characterisation<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n

      A shipping route is assumed as a set of straight segments or legs connecting waypoints, corresponding to locations of significant changes in the navigational behaviour of the ships such as changes in heading or velocity, which allows a compact representation of ships\u2019 motion.<\/p>\n\n

      A route turning section is automatically identified by clustering turning points detected in ship trajectories. A turning point in a ship trajectory is where a significant directional change in the ship trajectory is observed. The Douglas-Peucker (DP) algorithm typically used for ship trajectory compression can also be used for turning point detection. DBSCAN algorithm is applied for turning points clustering in this study. This algorithm forms clusters of elements based on the density of points in their neighbourhood.<\/p>\n\n

      The turning points detected along the ship routes passing the TTS off Cape Roca to the three ports are shown in Figure 4 (black points). Then, turning sections are identified by the spatial distribution of the coordinates of the turning points detected.<\/p>\n\n

      \n
      \n \"Clustering\n
      \n Figure 4 – Clustering of trajectory turning points<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n

      Figure 5 shows the spatial density distribution of the turning points. The study area is discretised in a 600*500 grid and the spatial density distribution of the turning points at each cell is calculated using the KDE method and depicted using the RGB (Red Green Blue) colour code. Once the density value of each grid cell is calculated, the colours of the grids are determined according to the corresponding turning points.<\/p>\n\n

      \n
      \n \"Turning\n
      \n Figure 5 – Turning sections identified based on the KDE<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n

      A statistical analysis is performed to study the maritime traffic on the route passing southbound dangerous traffic lane to Port of Sines, as tanker is the main ship type in this route. As shown in Figure 6, the ship route that passes the Southbound dangerous traffic lane to Port of Sines is divided by two turning sections derived above. In Leg 1 ships move southward toward the TSS off Cape Roca\u2019s Southbound dangerous traffic lane. Then, in Turning Section 1 ships turn east toward Sines Port in Leg 2.<\/p>\n\n

      \n
      \n \"Two\n
      \n Figure 6 – Two legs of the route passing divided by the turn section<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n

      Figure 7 illustrates the speed and COG distributions of ships in the two legs. In terms of speed distributions, it is seen that most ships in this route sail at 12-15 knots (70.9 % in Leg 1 and 66.2% in Leg 2, respectively). Figure 7(b) shows COG distributions at each leg. Obviously, there are significant differences between the traffic in each leg. One may notice two peaks in the histogram of COG, which correspond to the two directions of the legs.<\/p>\n\n

      \n
      \n \"Speed\n
      \n Figure 7 – Speed distributions and Course Over Ground (COG) distributions at the two legs<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n

      It is found that route width changes along the route. This indicates that the lateral distribution along the waterway needs to be investigated. The route width is estimated according to trajectory spatial distribution along the ship route. Once the route centreline is derived, the lateral distributions along legs 1 and 2 are calculated from the available AIS data at every 16 and 5 nautical miles (NM), respectively, as shown in Figure 8. The leg lateral distribution is approximated by a normal distribution, and then the 95% probability interval of the distribution is adopted as the route width. The grey box indicates the 95% confidence interval estimated by the series of route widths in a given section.<\/p>\n\n

      \n
      \n \"Width\n
      \n Figure 8 – Width distributions and uncertainty along the two legs<\/small><\/strong>\n <\/figcaption>\n <\/figure>\n<\/div><\/p>\n\n <\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      <\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t\n\t\t\t\t\t\t\n\t\t\t\t\t\tBack to tasks<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      <\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

      Task 2 Characterisation of maritime traffic and safe routes for ships A data-driven approach for maritime traffic network extraction based on Automatic Identification System (AIS) data has been proposed. A maritime traffic network, consisting of nodes that represent waypoint areas and navigational legs, is constructed to represent maritime traffic at a larger scale. The proposed …<\/p>\n

      Task 2<\/span> Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-793","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/pages\/793","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=793"}],"version-history":[{"count":130,"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/pages\/793\/revisions"}],"predecessor-version":[{"id":1790,"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=\/wp\/v2\/pages\/793\/revisions\/1790"}],"wp:attachment":[{"href":"https:\/\/monitraffic.tecnico.ulisboa.pt\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=793"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}