Deep flight track clustering based on spatial–temporal distance and denoising auto-encoding

• Published in: Expert systems with applications 2022-07, Vol.198, p.116733, Article 116733
• Main Authors: Liu, Guoqian, Fan, Yuqi, Zhang, Jianjun, Wen, Pengfei, Lyu, Zengwei, Yuan, Xiaohui
• Format: Article
• Language: English
• Subjects: ADS-B system; Air traffic management; Airspace; Airspeed; Aviation; Cluster analysis; Clustering; Denoising auto-encoding; Noise; Noise reduction; Similarity; Spatial; Temporal; Vector quantization
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2022.116733

The rapid development of the aviation industry imposes an urgent need for airspace traffic management. Meaningful clustering of flight tracks is of paramount importance for efficient operation and management of increasingly complex aerial space and traffic. Two key components exist in track clustering: similarity metric and clustering method. Most of the existing studies on track similarity metrics only consider the spatial coordinates of the track points without taking into consideration of the rich information of the track data, such as flight heading and flight speed, on the measurement of track similarity. In addition, temporal properties and the derived features of the flight tracks shall be utilized to reveal the underlying patterns and overcome distortions from noise. In this paper, we propose a track similarity based on the spatial–temporal characteristics of flight tracks and a Deep Temporal Clustering method using a denoising autoencoder. Our proposed method employs the Deep Temporal Denoising Auto-encoding network to extract the latent representations of the track sequences. By extending the idea of k-means clustering, Deep Temporal Clustering groups the flight tracks with a Time Clustering Layer. Experiments are conducted using Automatic Dependent Surveillance-Broadcast track data. In comparison with classical and state-of-the-art methods, among all cases, our Deep Temporal Clustering method achieved a much-improved performance of more than 57.3%. When we introduce noise to the track records and increase its magnitude, the performance of our method degrades but the trend slows down as the noise magnitude increases. The change is less than 7% and, in some cases, is close to zero, which demonstrates the robustness of our method to noise. •A novel metric of track similarity based on the spatial–temporal characteristics.•A deep trajectory clustering model based on the denoising autoencoder.•Improved performance for flight track clustering.