Home / Blog / Artificial Intelligence lands at Frankfurt Airport …

Artificial Intelligence lands at Frankfurt Airport …

A screenshot of incoming and outgoing traffic at Frankfurt Airport. Source: FligthAware

Just finished to read this news, and I should say I am impressed! If you like to get an inside look at the complexity of air traffic it surely makes for a good reading.

The news is about the decision of FRAPORT, the company managing the logistics at Frankfurt Airport, to use data from FlightAware to get information on the landing time of flights. Having an accurate landing time is essential in the operation of the airport logistics. You need to know when the aircraft will be there to synchronise bridge (or mobile air-stairs), refuelling, aircraft cleaning, passenger buses, catering replenishment, … and the allocation of people to carry out those tasks. It is a mind boggling endeavour for an airport like Frankfurt, that can only be managed through computer assisted scheduling, Yet, all this starts from the information of an accurate landing time.

Now, I would have bet, as I can imagine most of you would have, that the most accurate information on landing time can be provided by ATC (Air Traffic Control) at the airport. They are the one queuing and authorising airplanes to land so they have to know the exact time any airplane  will land! Indeed, that is the case. The problem is that ATC “knows” the landing time just 15 to 30 minutes before the actual landing (they receive hand over notice from the ATC controlling the contiguous airspace 10 to 15 minutes before it is going to take place and from that moment to the landing it takes 5 to 15 minutes, on average).

Having the possibility to know the landing time with good accuracy (on average) a hour before the actual landing, rather than 30 minutes before, will make quite a difference in optimising the logistics.

This is what FlightAware can provide. Of course, they cannot foresee if an ATC will decide to put an incoming airplane on an holding pattern because of a problem but on average they can provide a quite accurate estimate of the landing time.

An experienced air traffic controller, by looking at the radar and computer rendering of the air traffic in a certain area (like the one over Frankfurt airport shown in the picture) can tell at first glance if the traffic is normal or if there are problems and how those problems are affecting the flow of incoming aircrafts. This is what artificial intelligence is also good at. By using machine learning and pattern recognition FlightAware is able to come up with accurate prediction of landing time for each aircraft hours before they are due to land.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the Industry Advisory Board within the Future Directions Committee and co-chairs the Digital Reality Initiative. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.