(Advisor: Dr. Dimitri Mavris)
"Development of a Big Data Framework for the Classification and Analysis of Daily Airport Operations"
Friday, April 10 at 2:00 p.m.
Blue Jeans (https://bluejeans.com/435427297)
The Federal Aviation Administration (FAA) is the regulatory body in the United States responsible for the advancement, safety, and regulation of civil aviation. The FAA also oversees the development of the air traffic control system in the U.S. Over the years, the FAA has made tremendous progress in modernizing the National Airspace System (NAS) by way of technological advancements and the introduction of procedures and policies that have maintained the safety of the United States airspace. However, as with any other system, there is a need to continuously address evolving challenges pertaining to the sustainment and resiliency of the NAS. One of these challenges involves efficiently analyzing and assessing daily airport operations. In particular, there is a need to assess the impact and effectiveness of the implementation of Traffic Management Initiatives (TMI) and other procedures on daily airport operations, as this will lead to the identification of trends and patterns to inform better decision making. FAA analysts and researchers thus classify the daily operations of eight U.S. airports into three categories: “Good Days”, “Average Days”, and “Bad Days” as a means to assess their efficiency. However, this current process, known as the Operational Service Performance Criteria (OSPC) is characterized by a number of limitations.
First, the current process is time consuming and prone to human errors, as FAA analysts spend majority of their time extracting data from their sources on a daily basis. This also limits the ability of analysts to expand the scope of OSPC to include additional airports. Second, this classification is done using a broad set of predefined ranges of nine metrics across the eight airports, which may not be necessarily accurate across all airports. In addition, the current process assumes that each metric is weighted equally, which influences the classification of daily airport operations. Furthermore, there is a need to determine if classifying daily airport operations into three categories is the best suited approach. There is also a need to determine if the classification of daily airport operations should be airport specific or across airports, and if seasonality (fall, spring, summer) impacts the classification of daily airport operations. In addition, a process for efficiently comparing daily operations in similar and different airport categories is lacking.
Consequently, this dissertation aims to address these gaps by 1) developing a big data framework to automate the Operational Service Performance Criteria, from data extraction, through processing, analysis and storage, 2) leveraging supervised and unsupervised Machine Learning techniques to develop repeatable methodologies for the classification and analysis of daily airport operations, 3) determining the optimal number of categories needed to classify and assess daily airport operations, 4) leveraging supervised Machine Learning techniques to assess the degree to which a daily operation belongs to an airport category, and 5) determining if daily airport operations should be categorized on an individual airport basis or across multiple airports, and if seasonality (fall, spring, summer) impacts the classification of daily airport operations. This dissertation will also provide a repeatable methodology for assessing and providing insights into how the planning of Traffic Management Initiatives impacts daily airport operations.
It is expected that the outcomes of this dissertation will enable FAA analysts and researchers to efficiently assess daily airport operations, as this will lead to the identification of trends and patterns which will inform better decision making.
- Dr. Dimitri Mavris – School of Aerospace Engineering, Georgia Institute of Technology
- Dr. Olivia Pinon Fischer – School of Aerospace Engineering, Georgia Institute of Technology
- Mr. Tom Tessitore – Federal Aviation Administration, Georgia Institute of Technology