Air Traffic Prediction as a Video Prediction Problem Using Convolutional LSTM and Autoencoder

Abstract

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.