Reconstructing trajectories and extracting shipping routes between ports based on AIS data

The reliability of Automatic Identification System (AIS) data is often compromised due to equipment errors, human errors, and high ship density, leading to missing information in the raw data. This unreliability can hinder maritime traffic research and cause misjudgements by maritime authorities, potentially resulting in unnecessary losses. Therefore, reconstructing missing AIS data is beneficial for traffic management and safety monitoring by maritime administration. This study proposes a ship trajectory reconstruction method based on AIS data, which reconstructs missing trajectory points using the course over ground (COG) and the positions of existing AIS data. Additionally, a method for extracting inter-port shipping routes and calculating their spatio-temporal features is introduced. By employing adaptive BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering and trajectory resampling, optimal inter-port shipping routes are identified, and features such as average navigation time, speed, and draught are extracted. The proposed method was tested using real AIS data from the Bohai Sea area in January 2017. Results demonstrated the effectiveness of the method in reconstructing ship trajectories and extracting optimal shipping routes along with their spatio-temporal features. Comparative experiments with three popular trajectory reconstruction methods-Linear interpolation, Cubic interpolation, and B-spline interpolation-showed the superiority of the proposed method. This study provides new approaches for ship trajectory reconstruction and inter-port shipping route extraction based on AIS data. The results of this study are expected to provide more accurate and reliable data support for maritime management departments, enhance route planning, traffic efficiency, and risk warning capabilities, and offer significant practical value.