TA-LSTM: A Time and Attribute Aware LSTM for Deep Flight Track Clustering

Flight track clustering is the premise and foundation of air traffic control, and the effective latent representation of track data is key to the flight trajectory clustering. Long short-term memory (LSTM) is an important method to extract the features from trajectory data. However, LSTM ignores the irregular time intervals between track points and fails to effectively distinguish the importance of different attributes at each track point during feature extraction. In addition, the existing methods based on LSTM either ignore the distinct impacts of different attributes at each track point or simply assume that the influences of the previous track points on the subsequent ones decrease with time. In this paper, we propose a flight trajectory feature extraction unit called time and attribute LSTM (TA-LSTM) and a flight track clustering model based on TA-LSTM. The flight track clustering model consists of a feature extraction layer and a clustering layer. The feature extraction layer adopts TA-LSTM to obtain the latent representation of flight tracks, which adds a time control gate and an attribute control gate to the standard LSTM unit. The clustering layer takes the latent representation of flight tracks as the input to obtain the clustering results. We conduct experiments using Automatic Dependent Surveillance-Broadcast track data provided by VariFlight. In comparison with popular and state-of-the-art methods, the proposed method obtains superior performance in three widely used evaluation metrics, i.e., Silhouette Coefficient, Calinski-Harabaz index and Davies–Bouldin index.