A novel method for restoring the trajectory of the inland waterway ship by using AIS data

• Three rules are built to identify the inaccurate data and cleanse AIS data.
• These three rules can effectively identify and remove the inaccurate data.
• The trajectory of the inland ship can be characterised by three trajectory types.
• A novel method of restoring the full trajectory is designed.
• The proposed method can be used to restore a trajectory in an effective manner.

The trajectory of the inland waterway ship is important and useful in analysing the features of the ship behaviour and simulating traffic flows. In the proposed research, a method is designed to restore the trajectory of an inland waterway ship based on the Automatic Identification System (AIS) data. Firstly, three rules are developed to identify and remove the inaccurate data, based on the reception range of the received AIS data and the manoeuvring characteristics of the inland waterway ship. Secondly, the method of restoring the full trajectory incorporating navigational features of the inland waterway ship is proposed to model the ship trajectory. The trajectory is characterised by three types (line, curve and arc) and five steps (line, curve, arc, curve and line) during the turning section. In order to validate the proposed method, the AIS data of two inland waterway ships collected from three AIS-base-stations is selected for the analysis, all inaccurate AIS data is identified and removed by the use of three cleansing rules. The results show that the three developed rules can effectively identify the inaccurate AIS data. The AIS data collected by an AIS-shipboard-unit is then used to: (1) restore the ship trajectory, and (2) validate the proposed method by comparing the reconstituted trajectories with the actual trajectory. This actual trajectory is determined from intermediate higher frequency Global Positioning System (GPS) data and collected from the AIS-shipboard-unit. The residual errors are calculated as the differences between the estimated latitude values of the restored trajectory functions and the real latitude values of the GPS data. Three alternative methods of trajectory restoring are also evaluated. The results show that the proposed method can be used to restore the full trajectory in an effective manner by using AIS data.