Models are proposed to estimate the performance of Ground Delay Programs as air traffic management initiatives. We apply Random Forest and Gradient-Boosted Forest regression techniques within the context of Geographically Weighted Regression. We estimate both the mean and 90th percentile responses for two performance indicators: average arrival delay and the number of cancelled arrivals.
|Original language||English (US)|
|State||Published - 2017|
|Event||12th USA/Europe Air Traffic Management Research and Development Seminar, ATM 2017 - Seattle, United States|
Duration: Jun 26 2017 → Jun 30 2017
|Other||12th USA/Europe Air Traffic Management Research and Development Seminar, ATM 2017|
|Period||6/26/17 → 6/30/17|
Bibliographical noteFunding Information:
ACKNOWLEDGMENT The data for this study were processed and graciously provided to us by Sreeta Gorripaty, Yulin Liu, Mark Hansen, and Alexei Pozdnukhov of the University of California at Berkeley and Kennis Chan and John Schade of ATAC, Inc. This work was funded under NASA grant no. NNX14AJ79A.
- Air traffic management
- Delay prediction
- Ground delay program