Predicting Estimate Departure Clearance Times Based on Surface Weather Observations for Major Hub Airports: A Vector Autoregression Approach
group
What campus are you from?
Daytona Beach
Authors' Class Standing
Shlok Misra, Graduate Student
Lead Presenter's Name
Shlok Misra
Faculty Mentor Name
Dr. Dothang Truong
Abstract
Commercial air travel in the United States has increased significantly in the past decade. While the reasons for air traffic delays can vary, weather is the primary cause of flight cancellation and delays in airports in the United States. Air Traffic Control centers utilize Traffic Management Initiatives such as Ground Stop and Estimate Departure Clearance Times (EDCT) to manage traffic into and out of affected airports. Airline dispatchers and pilots monitor EDCTs to adjust flight blocks and flight schedules to reduce the impact on the airline’s operating network. In this paper, a time-series modeling technique was used to predict delays which allows us to enhance dispatch operations and airline management. A time series vector autoregression model was created to predict EDCTs at Charlotte Douglas International Airport based on hourly surface weather observations. The initial model was created and validated with 26 lags, and then a regression equation was created with 22 independent variables. Precipitation values up to five hours before the EDCT prediction period were found to have the highest impact on the EDCT prediction. Weather-related variables up to six hours before the prediction time were used to develop the regression equation, including altimeter, precipitation, temperature, visibility, and relative humidity. The results and the model development techniques are expected to serve as a theoretical foundation for further analysis of the effectiveness of time series forecasting for EDCT prediction.
Did this research project receive funding support from the Office of Undergraduate Research.
No
Predicting Estimate Departure Clearance Times Based on Surface Weather Observations for Major Hub Airports: A Vector Autoregression Approach
Commercial air travel in the United States has increased significantly in the past decade. While the reasons for air traffic delays can vary, weather is the primary cause of flight cancellation and delays in airports in the United States. Air Traffic Control centers utilize Traffic Management Initiatives such as Ground Stop and Estimate Departure Clearance Times (EDCT) to manage traffic into and out of affected airports. Airline dispatchers and pilots monitor EDCTs to adjust flight blocks and flight schedules to reduce the impact on the airline’s operating network. In this paper, a time-series modeling technique was used to predict delays which allows us to enhance dispatch operations and airline management. A time series vector autoregression model was created to predict EDCTs at Charlotte Douglas International Airport based on hourly surface weather observations. The initial model was created and validated with 26 lags, and then a regression equation was created with 22 independent variables. Precipitation values up to five hours before the EDCT prediction period were found to have the highest impact on the EDCT prediction. Weather-related variables up to six hours before the prediction time were used to develop the regression equation, including altimeter, precipitation, temperature, visibility, and relative humidity. The results and the model development techniques are expected to serve as a theoretical foundation for further analysis of the effectiveness of time series forecasting for EDCT prediction.