(Georgia Institute of Technology, 2019-06)
Mangortey, Eugene; Pinon, Olivia J.; Puranik, Tejas G.; Mavris, Dimitri N.
Traffic Management Initiatives (TMI) such as Ground Delay Programs (GDP) are instituted by traffic management personnel to address and reduce the impacts of constraints in the National Airspace System. Ground Delay Programs are initiated whenever demand is projected to exceed an airport’s acceptance rate over a lengthy period of time. Such instances occur when an airport is affected by conditions such as inclement weather, aircraft congestion, runway-related incidents, equipment failures, and other causes that do not fall in these categories. Over the years, efforts have been made to reduce the impact of Ground Delay Programs on airports and flight operations by predicting their occurrence. However, these efforts have largely focused on weather-related Ground Delay Programs, primarily due to a lack of access to comprehensive Ground Delay Program data. There has also been limited benchmarking of Machine Learning algorithms to predict the occurrence of Ground Delay Programs. Consequently, this research 1)fused data from the Traffic Flow Management System (TFMS), Aviation System Performance Metrics (ASPM), and Automated Surface Observing Systems (ASOS) datasets, and 2) leveraged supervised Machine Learning algorithms to develop prediction models as a means to predict the occurrence of weather and volume-related Ground Delay Programs. The Kappa Statistic evaluation metric revealed that Boosting Ensemble was the best suited algorithm for predicting the occurrence of weather and volume-related Ground Delay Programs.
(Georgia Institute of Technology, 2019-01)
Mangortey, Eugene; Gilleron, Jerome; Dard, Ghislain; Pinon, Olivia J.; Mavris, Dimitri N.
The Federal Aviation Administration (FAA) is primarily responsible for the advancement, safety, and regulation of civil aviation, as well as overseeing the development of the air traffic control system in the United States. As such, it is faced with tremendous amounts of data on a daily basis. This data, which comes in high volumes, in various formats, from disparate sources and at various frequencies, is used by FAA analysts and researchers to make accurate forecasts, improve the safety and operational performance of their operations, and streamline processes. However, by its very nature, aviation Big Data presents a number of challenges to analysts: it impedes their ability to get a real-time picture of the state of the system, identify trends and operational patterns, make real-time predictions, etc. As such, the overarching objective of the present effort is to support FAA through the development of a data fusion framework to support the analysis of aviation Big Data. For the purpose of this research, three datasets were considered: System-Wide Information Management (SWIM) Flight Publication Data Service (SFDPS), Traffic Flow Management System (TFMS), and Meteorological Terminal Aviation Routine (METAR). The equivalent of one day of data was retrieved from each dataset, parsed and fused. A use case was then used to illustrate how a data fusion framework could be
used by FAA analysts and researchers. The use case focused on predicting the occurrence of weather-related Ground Delay Programs (GDP) at the Newark (EWR), La Guardia (LGA), and Boston Logan (BOS) International Airports. This involved developing a prediction model using the Decision Tree Machine Learning technique. Evaluation metrics such as Matthew’s
Correlation Coefficient were then used to evaluate the model’s performance. It is expected that a data fusion framework, once integrated within the FAA’s Computing and Analytics Shared Services Integrated Environment (CASSIE) could be used by analysts and researchers alike to identify trends and patterns and develop efficient methods to ensure that the U.S. civil and
general aviation remains the safest in the world.