Spectrum Optimization for Advanced Air Mobility using Machine Learning Methods

The emergence of new aerial vehicles into the airspace and the continued growth of aviation operations will result in an increased demand for voice and data communications throughout the National Airspace System (NAS). However, the continued use of existing aviation spectrum allocations will not meet the anticipated needs of future aerospace applications; as a result, a new approach to aviation spectrum management is needed to support the forecasted needs of new airspace users. The National Aeronautics and Space Administration (NASA) is investigating the use of recent advancements in artificial intelligence (AI) and machine learning (ML) to implement a novel spectrum management approach that allows for the intelligent utilization of aviation spectrum throughout the airspace. This thesis investigates the use of ML and AI to jointly manage communications channel selection and airspace resources to improve and optimize the overall frequency spectrum utilization in the airspace. The technical investigation considers various airspace communications configurations, including air-ground and air-air communications, and can be applied to the existing air traffic control (ATC) system, as well as to future applications, such as the emerging Advanced Air Mobility (AAM) initiative. To support the evaluation of the proposed concepts and technologies, a modeling and simulation capability has been developed, which will continue to evolve in support of new and advanced airspace applications. It is anticipated that this proposed spectrum management concept will allow for increased spectrum utilization efficiency and enhanced airspace capacity, which will better serve the needs of future airspace applications.