Amelia-48: An airport surface movement dataset

Amelia-48 is a large-scale airport surface movement dataset collected using the System Wide Information Management (SWIM) Surface Movement Event Service (SMES). With data collection beginning in December 2022, the ~30TB dataset currently provides a year’s worth of data and covers 48 airports and TRACON facilities within the US National Airspace System.

NOTE: Below we provide instructions on how to access the pre-processed trajectory data which was used for trajectory forecasting. This data corresponds to the 10 airports we used for our experiments in the paper.

Additionally, we provide instructions on how to download the general raw dataset, which contains the full 48 airport data.

Finally, we also provide a dataset tracker which summarizes the available assets for each airport.

Pre-processed Data

We provide the pre-processed trajectory data used for our trajectory forecasting experiments.

Click the link below to download our dataset:

The downloaded dataset follows this structure:

|-- amelia
    |-- assets
    |    | -- airport_icao
    |    |    | -- bkg_map.png
    |    |    | -- limits.json
    |    |    | -- airport_code_from_net.osm
    |    | ...
    |-- graph_data_a10v01os
    |    | -- airport_icao
    |    |    | -- semantic_graph.pkl
    |    |    | -- semantic_airport_icao.osm
    |    |    | -- semantic_graph.png
    |    | ...
    |-- graph_data_a48v01os
    |    | -- airport_icao
    |    |    | -- semantic_graph.pkl
    |    |    | -- semantic_airport_icao.osm
    |    |    | -- semantic_graph.png
    |    | ...
    |-- traj_data_a10v08
    |    | -- airport_icao
    |    |    | -- AIRPORT_ICAO_<unix_timestamp>.csv
    |    |    | ...
    |    |    | ...
    |    | ...

Assets

The assets folder has a subfolder for each airport (uses the airport’s ICAO) containing the following:

bkg_map.png: visual representation of the map, obtained using OpenStreetMap (OSM).
limits.json: JSON file containing the Airport’s extents.
airport_icao.osm: the airport’s map in OSM format.

Graph Data (Processed Map Information)

To generate the processed map information, we used AmeliaMaps.

The graph_data_a10v01os folder has a subfolder for each airport containing semantic graphs representation obtained using AmeliaMaps. Each sub-folder contains the following files:

semantic_graph.pkl: contains the vectorized map graph with semantic attributes.
semantic_airport_icao.osm: the semantic representation of the graph in OSM format
semantic_graph.png: visual representation of the graph. Just shown for reference.

NOTE this folder contains the graphs for the 10 airports used in our training experiments. The full set of 48 maps is in the folder graph_data_a48v01os.

Trajectory Data

The traj_data_a10v08 folder has a subfolder for each airport containing the trajectory data in CSV format. Each file within an airport’s subfolder represents an hour of data.

The files are named following the format AIRPORT_ICAO_<unix_timestamp>.csv. Each contains trajectory information in the following format:

**Table 1.** Processed Trajectory Data Fields
Field	Unit	Description
Frame	#	Timestamp
ID	#	STDDS Agent ID
Range	km	Distance from airport datum
Bearing	rads	Bearing angle w.r.t North
Altitude	feet	Agent altitude (Mean Sea Level)
Speed	knots	Agent speed
Heading	degrees	Agent heading
Type	int	Agent type: {0: aircraft 1: vehicle, 2: unknown}
Lat	decimal degrees	Agent's latitude
Lon	decimal degrees	Agent's longitude
x	km	Agent's local x Cartesian position
y	km	Agent's local y Cartesian position
Interp	boolean	Interpolated data point flag

The processed data contains 1 month of data for each of the 10 airports. The airports are as follows:

Boston-Logan Intl. Airport - Jan 2023
Newark Liberty Intl. Airport - Mar 2023
Ronald Reagan Washington Natl. Airport - April 2023
John F. Kennedy Intl. Airport - April 2023
Los Angeles Intl. Airport - May 2023
Chicago-Midway Intl. Airport - June 2023
Louis Armstrong New Orleans Intl. Airport - July 2023
Seattle-Tacoma Intl. Airport - Aug 2023
San Francisco Intl. Airport - Sept 2023
Ted Stevens Anchorage Intl. Airport - Nov 2023

Raw Data

In order to download and process data for the other airports, please follow instructions below:

Downloading and processing raw trajectory data

To download the raw data, please follow the instructions in AmeliaSWIM on how to use the download_raw.py script.
To process the raw data, please follow the instructions in AmeliaSWIM on how to use the process.py script. The resulting data will be saved as CSV files containing the information in Table 1.

Downloading and processing map data

To download and process the map data, please follow the instructions in AmeliaMaps on how to use the processing scripts.

Data Tracker

In the following table, you can find the status of the data processing for each airport. The table includes the following columns:

Airport: Airport's Full Name.
Airport ICAO : Airport's code.
Raw Data: Indicates if raw trajectory data is available for the airport.
Processed Data: Indicates if we provide processed data for this airport (i.e., in the format listed in the table above).
Airport Map: Indicates if we provide an image representation of the airport's map.
Semantic Graph: Indicates if we provide a semantic graph representation of the airport's map.
Fence: Indicates if we provide a GeoFence of the airport's map. GeoFence is used for capturing data within a region of interest.
Limits: Indicates if we provide the airport's extent information.

**Table 2.** Data tracker. The airplane icon () indicates the type of data is available for the airport.
	Airport	Airport ICAO	Trajectory		Map
	Airport	Airport ICAO	Raw Data	Processed Data	Airport Map	Semantic Graph	Fence	Limits File
1	Seattle-Tacoma Intl. Airport	KSEA
2	Newark Liberty Intl. Airport	KEWR
3	Los Angeles Intl. Airport	KLAX
4	Ted Stevens Anchorage Intl. Airport	PANC
5	Boston-Logan Intl. Airport	KBOS
6	Ronald Reagan Washington Natl. Airport	KDCA
7	San Francisco Intl. Airport	KSFO
8	Chicago-Midway Intl. Airport	KMDW
9	John F. Kennedy Intl. Airport	KJFJ
10	Louis Armstrong New Orleans Intl. Airport	KMSY
11	McCarran Intl. Airport	KLAS
12	Milwaukee Mitchell Intl. Airport	KMKE
13	Memphis Intl. Airport	KMEM
14	George Bush Intercontinental Airport	KIAH
15	Washington Dulles Intl. Airport	KIAD
16	Phoenix Sky Harbor Intl. Airport	KPHX
17	Salt Lake City Intl. Airport	KSLC
18	Denver Intl. Airport	KDEN
19	Kansas City Intl. Airport	KMCI
20	Cincinnati/Northern Kentucky Intl. Airport	KCVG
21	Cleveland Hopkins Intl. Airport	KCLE
22	Charlotte Douglas Intl. Airport	KCLT
23	San Diego Intl. Airport	KSAN
24	Orlando Intl. Airport	KMCO
25	William P. Hobby Airport	KHOU
26	Dallas/Fort Worth Intl. Airport	KDFW
27	Detroit Metropolitan Wayne County Airport	KDTW
28	Louisville Muhammad Ali Intl. Airport	KSDF
29	O'Hare Intl. Airport	KORD
30	John Wayne Airport	KSNA
31	Portland Intl. Airport	KPDX
32	Baltimore/Washington Intl. Thurgood Marshall Airport	KBWI
33	Philadelphia Intl. Airport	KPHL
34	Fort Lauderdale-Hollywood Intl. Airport	KFLL
35	Minneapolis-Saint Paul Intl. Airport	KMSP
36	Daniel K. Inouye Intl. Airport	KHNL
37	Daytona Beach Intl. Airport	KDAB
38	Miami Intl. Airport	KMIA
39	Hartsfield-Jackson Atlanta Intl. Airport	KATL
40	Pittsburgh Intl. Airport	KPIT
41	Bradley Intl. Airport	KBDL
42	T.F. Green Airport	KPVD
43	St. Louis Lambert Intl. Airport	KSTL
44	LaGuardia Airport	KLGA
45	Austin-Bergstrom Intl. Airport	KAUS
46	Norman Y. Mineta San Jose Intl. Airport	KSJC
47	Oakland Intl. Airport	KOAK
48	Nashville Intl. Airport	KBNA

BibTeX

If you find our work useful in your research, please cite us!

@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},
}