AIS data repair model based on generative adversarial network

Automatic Identification System (AIS) is a navigation aid system widely used in maritime safety and communication. However, due to issues with AIS devices, the data collected by AIS will inevitably contain missing and abnormal problems. To enhance the quality of AIS data, this paper introduces a proposed AIS data repair model named TLGAN. The model is constructed with Generative Adversarial Network (GAN), which combines Temporal Convolutional Network (TCN) and Bi-directional Long Short-Term Memory (BiLSTM) to repair AIS data. Through the confrontation training between the generator and discriminator, the model is urged to capture different features of ship data, ensuring that the data generated by the generator closely approximates the real distribution. Compared with different baseline models, the proposed model exhibits superior performance in repairing AIS data. Furthermore, for ship trajectory data, the paper employs Savitzky-Golay (SG) filtering and cubic exponential smoothing techniques to optimize the trajectory data, further improving the quality of the repair results.