基于时空特征融合的TCNformer船舶航迹长期预测

Long Term Prediction of Ship Trajectories Using TCNformer Based on Spatiotemporal Feature Fusion

船舶轨迹预测在多种海事任务中发挥着重要的作用,虽已提出了多种时序模型解决航迹预测的问题,但船舶轨迹固有的异构型和多模式仍然面临诸多挑战,且在轨迹长期预测任务中存在较高的预测误差。针对船舶轨迹长期预测的实际应用需求,设计了1种新的AIS数据离散高维表示方法和1种新的损失函数,并将预测问题建模为分类问题,结合时间卷积网络(Temporal Convolutional Network,TCN)和Transformer模型搭建了1种新的模型,称为TCNformer,利用融合的时间维度特征和空间维度特征,通过有效捕捉AIS数据的长期依赖性,预测未来几个小时船舶位置。在公开的AIS数据集上的测试表明,所提方法相较于其他时序模型预测性能提升2倍,最长预测时间范围延长约3.8倍,满足船舶航迹长期预测的要求。

Ship trajectory prediction plays an important role in various maritime applications.Although multiple time series models have been proposed to solve the problem of trajectory prediction,the inherent heterogeneity and multimodality 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 classification 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 publicly 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.