Date on Master's Thesis/Doctoral Dissertation


Document Type

Master's Thesis

Degree Name

M. Eng.


Electrical and Computer Engineering

Degree Program

JB Speed School of Engineering

Committee Chair

Li, Hongxiang

Committee Co-Chair (if applicable)

Elmaghraby, Adel

Committee Member

Elmaghraby, Adel

Committee Member

Faul, Andre

Committee Member

Zurada, Jacek

Author's Keywords

Flight Trajectory Prediction; Hybrid-Recurrent Neural Network; Aviation Communications; Air Traffic Management; Communications Demand


The development of future technologies for the National Airspace System (NAS) will be reliant on a new communications infrastructure capable of managing a limited spectrum among aircraft and ground systems. Emerging approaches to this spectrum allocation task mostly consider machine learning techniques reliant on aircraft and Air Traffic Control (ATC) sector data. Much of this data, however, is not directly available. This thesis considers the development of two such data products: the 4D trajectory (latitude, longitude, altitude, and time) of aircraft, and the anticipated airspace utilization and communication demand within an ATC sector. Data predictions are treated as a time series forecast challenge and addressed via the development of deep learning models with some form of recurrence. For each data product, relevant datasets are explored and an architecture search is conducted to identify and optimize a deep learning model. To this end, current efforts have primarily addressed trajectory prediction. Flight and weather data for the 4D trajectory prediction have been identified and preprocessed; initial comparisons of weather data have been used to hypothesize useful combinations; and initial model architectures have been identified for comparative development. Future work seeks to finalize training efforts toward trajectory prediction and address the task of airspace demand prediction.