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

Aerospace

Hyewook Kim¹  Keumjin Lee¹ 

[1] Department of Air Transportation and Logistics, Korea Aerospace University, Deogyang-gu, Goyang-si 10540, Gyeonggi-do, Korea;

关键词: air traffic prediction;    trajectory prediction;    deep learning;    video prediction;   

DOI  :  10.3390/aerospace8100301

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown