MART:Ship Trajectory Prediction Model Based on Multi-Dimensional Attribute Association of Trajectory Points

Ship trajectory prediction plays an important role in numerous maritime applications and services. With the development of deep learning technology, the deep learning prediction method based on AIS (Automatic Identification System) data has become one of the hot topics in current maritime traffic research. However, the academic community currently generally focuses on connections between trajectory points while ignoring correlations among the dynamic information of trajectory points and the po-tential information of the dynamic information itself. Aiming at the problem of insuf-ficient modeling of the relationships among dynamic information in ship trajectory prediction, we propose MART (Multidimensional Attribute Relationship Transformer) model. This model introduces a simulated trajectory training strategy to obtain the Association Loss (AssLoss) for learning the associations among different dynamic in-formation; and uses the Distance Loss (DisLoss) to integrate the relative distance in-formation of the attribute embedding encoding to assist the model in understanding the relationships among different values in the dynamic information. We test the model on two AIS datasets, and the experiments show this model outperforms existing models (such as seq2seq, etc.) in long-term prediction tasks. This study reveals the im-portance of the relationship between attributes and the relative distance of attribute values in spatiotemporal sequence modeling.