Accurate prediction of future air traffic situations is an essential task in many applications in air traffic management. This paper presents a new framework for predicting air traffic situations as a sequence of images from a deep learning perspective. An autoencoder with convolutional long short-term memory (ConvLSTM) is used, and a mixed loss function technique is proposed to generate better air traffic images than those obtained by using conventional L1 or L2 loss function. The feasibility of the proposed approach is demonstrated with real air traffic data.

In case of South Korea, the airspace which airlines can operate is extremely limited due to the military operational area located within the Incheon flight information region. As a result, safety problems such as mid-air collision between aircraft or Traffic alert and Collision Avoidance System Resolution Advisory (TCAS RA) may occur with higher probability than in wider airspace. In order to prevent such safety problems, an mid-air collision risk detection model based on Detect-And-Avoid (DAA) well clear metrics is investigated. The model calculates the risk of mid-air collision between aircraft using aircraft trajectory data. In this paper, the practical use of DAA well clear metrics based model has been validated. Aviation safety data such as aviation safety mandatory report and Automatic Dependent Surveillance Broadcast is used to measure the performance of the model. The attributes of individual aircraft track data is analyzed to correct the threshold of each parameter of the model.

No abstract