Page 18 - AAA MARCH - APRIL 2019 Online Magazine

TO AIRSIDE TO CHECK-IN LARGE
NUMBERS OF REBOOKED
PASSENGERS,”A SITA spokesman

Flight Delay Prediction
SITA Lab has also successfully demonstrated,
using machine learning, that it is able to pre-
dict flight delays up to six hours before their
expected arrival. This breakthrough will have
a profound impact on providing more respon-
sive airport operations and limit the impact on
passengers.

Flight delays and disruption costs the indus-
try an estimated US$25 billion every year. The
impact of this disruption was identified as one excited by the possibility that we could provide predictions on
of the biggest challenges facing air transport flight arrivals. Over a six-month period, we used various sources
today. In 2017, SITA Lab, using commonly avail- of information such as weather, NOTAMs (notice to airmen), flight
able data and machine learning, successfully movements and other flight data to predict six hours ahead of time
demonstrated that they could predict flights the expected arrival time,” says SITA Lab’s Thierry le Gall. “Using
delays up to six hours in advance. sophisticated algorithms, we were able to provide an accurate pre-

The team began working with a major Asian diction of within 15 minutes of the flight arrival for around 80 percent
airport that were seeking a solution that would of flights 6 hours before touch down. Building on our successes,
provide better insight into aircraft arrival and we are improving the prediction accuracies as well as extending
departures. Key challenges facing the airport the predictions up to 12 and 24 hours before gate arrival.
were that they had limited visibility on arrival
traffic and high variability of landing times due Of course, these performances can vary over time and cannot be
to weather and congestion. This was having guaranteed for all airports. But the beauty of machine-learning is
a dramatic impact on the airport’s ability to the more we can provide quality data and the more we learn from
effectively manage everything from allocating past predictions, the more accurate our predictions become.’ “We
runway slots and gates to providing the right believe that by providing more certainty to the fluid nature of flight
resources needed for aircraft turnaround and movements and the implementation of proactive planning of the
personnel at security or immigration. industry’s resources in anticipation of this fluidity, will be a major
“When we approached the airport, they were step forward,” says Sebastien Fabre, VP Airports at SITA.

AI Easing Airport Security
AI is also helping in airport security, as individuals with limited mobil-
ity are able to make their way through the security process with
ease. The process is also quicker than traditional airport security
measures, resulting in shorter lines.

Recently, Denver International Airport adopted the use of Rohde
and Schwarz’s new rapid body scanner during TSA screening.

18 | March/April 2019 WWW .GBP .COM.SG/ AAA