Long Term Prediction of Ship Trajectories Using TCNformer Based on Spatiotemporal Feature Fusion
Ship trajectory prediction plays an important role in various maritime applications.Although multiple time se-ries models have been proposed to solve the problem of trajectory prediction,the inherent heterogeneity and multimodal-ity of ship trajectories still pose many challenges,and there are high prediction errors in long-term trajectory prediction tasks.In response to the practical application needs of long-term prediction of ship trajectories,a new discrete high-dimensional representation of AIS data and a new loss function are designed to model the prediction problem as a classifi-cation problem.A new model called TCNformer is constructed by combining temporal convolutional network(TCN)and transformer network,which effectively captures the long-term dependencies of AIS data using fused temporal and spatial features,to predict the position of the ship in the coming hours.The performance of the proposed model is tested on a pub-licly available AIS dataset.Compared to other time series models,the predictive performance is improved by 2 times,and the longest prediction time range is extended by about 3.8 times,meeting the requirements for long-term prediction of ship trajectories.
long term trajectory predictionTCN networktransformer networkintegration of spatiotemporal featuresAIS data
万方数据
维普
