Automatic Identification System (AIS) Data Supported Ship Trajectory Prediction and Analysis via a Deep Learning Model

Automatic Identification System (AIS) data-supported ship trajectory analysis consistently helps maritime regulations and practitioners make reasonable traffic controlling management decisions. Significant attentions are paid to obtain an accurate by learning data feature patterns in a feedforward manner. A may change her moving status avoid potential accident inland waterways, thus, the variation pattern differ from previous samples. The study proposes novel exploitation prediction framework with help of bidirectional long short-term memory (LSTM) (Bi-LSTM) model, which extracts intrinsic features backward manners. We have evaluated proposed performance single multiple scenarios. indicators mean absolute error (MAE), percentage (MAPE) square (MSE) suggest that Bi-LSTM model can obtained satisfied performance.