OPENSKY NETWORK

SKYSHARK heavily relies on data sourced from the OpenSky Network . Established by researchers for researchers, the OpenSky Network is a unique platform.

The OpenSky Network is a non-profit community-based receiver network which has been continuously collecting air traffic surveillance data since 2013. Unlike other networks, OpenSky keeps the complete unfiltered raw data and makes it accessible to academic and institutional researchers. With over 30 trillion ADS-B, Mode S, TCAS and FLARM messages collected from more than 5000 sensors around the world, the OpenSky Network exhibits the largest air traffic surveillance dataset of its kind. The mission of our non-profit association is to support open global air traffic research by universities and other not-for-profit institutions.

OpenSky Network offers a range of data access methods. In addition to a comprehensive REST API, they provide various programming packages for Python and other languages, as well as an Trino Shell for accessing historical data. The data can be utilized for research and by non-profit organizations, subject to their terms of use.

At SKYSHARK, we offer a reference dataset derived from OpenSky's extensive collection, ideal for benchmarking your system against a standardized dataset. If you're interested in testing your system with additional data or real-time data, click here (reference here) or directly contact OpenSky Network to access their historical records.

Creating Flight Schedules

Obtaining airline flight plans without significant financial investment is not feasible due to the high cost associated with commercial services. To overcome this issue, we create our own flight schedules by querying individual flights using the REST API provided by OpenSky Network. Callsigns consist of an airline abbreviation (e. g., LH for Lufthansa) and a flight number (e. g., 101). Private or military aircrafts may not have callsigns or their meaning is unknown. We determine flight takeoff and landing by monitoring the on_ground field in each state. Changes from true to false indicate takeoff, and vice versa indicate landing. By storing and rounding the timestamps of these transitions, we obtain a rough flight schedule that aligns with recorded flights. It is important to note that this flight schedule is incomplete and not entirely accurate but serves the purpose of the benchmark.