The prediction of vessel berthing trajectory can provide reference for the supervision of vessel traffic services, and has high application value in the early warning of vessel collision, grounding and other accidents. Aiming at the problem that it is difficult to predict the movement trend of vessels in the crowded port water, this paper establishes a vessel berthing trajectory prediction model based on bidirectional Gated Recurrent Unit (Bi-GRU). By learning the AIS data of Tianjin port, the vessel trajectories are predicted and compared with other recurrent neural network models such as LSTM and GRU. The experimental results show that the prediction method based on Bi-GRU model has higher accuracy and smaller error.
Vessel trajectory prediction based on AIS data and bidirectional GRU
2020-07-01
481103 byte
Conference paper
Electronic Resource
English
Vessel Trajectory Prediction Method Based on the Time Series Data Fusion Model
DOAJ | 2024
|