Traffic Flow Prediction for UTM Application: A Deep Learning Approach

Abstract

Over the past few years, the research community has focused greatly on predicting air traffic flows, yielding remarkable outcomes. We found that existing literature in the field mainly covers prediction of air traffic flows for conventional aircraft. However, there is limited research about prediction of air traffic flows for Uncrewed Aircraft Traffic Management (UTM). This research study proposes a deep learning-based approach to predict air traffic congestion in the context of UTM over a period of three minutes. The use of the model aims to address congestion considering air traffic uncertainties instead of addressing the conventional issues of trajectory prediction or conflict detection and resolution. Our model also considers the influence of recreational users who fly UAVs at random times, during the execution of the above essential missions. Further, the effects of airspace structure configurations like static No-Fly Zones (NFZ), airfields with variable availability for drone flights, recreational areas, emergency UTM operation and environmental factors such as weather conditions have also been studied. The proposed model shows better performance compared to other approaches such as the Shallow neural networks and regression models.