A Large Model and Dataset for Airport Surface Movement Forecasting


Our Motivation

The growing demand for air travel requires technological advancements in air traffic management as well as mechanisms for monitoring and ensuring safe and efficient operations.

A close call…

BOS Incursion
A runway incursion at Boston-Logan Intl. Airport (2x speed)
February 27, 2023


To improve airport safety and efficiency and encourage further research in this direction we introduce Amelia, a large-scale dataset of airport surface movement and a toolkit for data analysis, visualization, benchmarking, and behavior modeling.

Our dataset, Amelia-48 comprises more than a year’s worth of data collection across 48 airports and TRACON facilities within the US National Airspace System, which is ∼50TB of raw data.

Additionally, inspired by the success of motion prediction models in the AV domain for safety monitoring and multi-agent coordination, we introduce Amelia-TF, a transformer-based large multi-agent multi-airport trajectory forecasting model trained on 292 days or over 9B tokens of position data encompassing 10 different airports.



Keywords

Aviation | Machine Learning | Deep Learning | Data Science

Trajectory Prediction | Anomaly Detection | Safety



Our Framework






Papers


plane Amelia: A Large Model and Dataset for Airport Surface Movement Forecasting

Ingrid Navarro *, Pablo Ortega-Kral *, Jay Patrikar *, Haichuan Wang, Zelin Ye, Jong Hoon Park, Jean Oh and Sebastian Scherer

*Denotes equal contribution

@inbook{navarro2024amelia,
  author = {Ingrid Navarro and Pablo Ortega and Jay Patrikar and Haichuan Wang and Zelin Ye and Jong Hoon Park and Jean Oh and Sebastian Scherer},
  title = {AmeliaTF: A Large Model and Dataset for Airport Surface Movement Forecasting},
  booktitle = {AIAA AVIATION FORUM AND ASCEND 2024},
  chapter = {},
  pages = {},
  doi = {10.2514/6.2024-4251},
  URL = {https://arc.aiaa.org/doi/abs/10.2514/6.2024-4251},
  eprint = {https://arc.aiaa.org/doi/pdf/10.2514/6.2024-4251},
}