Embracing Artificial Intelligence in aviation and air traffic management

I was in Brussels last month for Eurocontrol’s Artificial Intelligence in Aviation event for a chance to cut through the hype and look at real, practical ways in which this disruptive technology can help transform how the aviation industry works, and the challenges that exist in getting there.

Together with our digital tower partners, Searidge Technologies, we were asked to demonstrate the work we’re currently doing at Heathrow using AI to reduce weather related delays.

Over 300 delegates heard from speakers, from inside and beyond the aviation industry, from Airbus to IBM all of whom are playing leading roles in the adoption of AI, and it was a fascinating debate. Drawing on her experience working in healthcare, AI and Machine Learning scientist Loubna Bouarfa, talked about the need to trust AI systems in uncertain environments, while Marc Fontaine of Airbus highlighted the need to get data out of silos and the difficult of replacing legacy systems in a 24/7 operational environment.

One figure that caught my attention was the fact that less than 10% of the data produced by the industry in Europe is actually used. Grazia Vittadini, Chief Technology Officer of Airbus, and Jean Ferre, VP ATM at Thales, joined with me, during our panel session, to call for the adoption of a more open approach to how data is stored and shared in order to unleash its latent value.

This will need partnerships to be established between OEMs and ANSPs, airports and aircraft manufacturers/operators to make this a reality and enable a more ‘application’ based approach to technology solution deployment in air traffic management.

That ethos of harnessing the power of operational data has been the cornerstone of what Searidge Technologies have been working on for the past two years. Searidge began considering the ATM applications of AI by building on the technical expertise developed using Machine Learning and neutral networks to enhance tracking and detection capability in image processing.

Neural networks work by analysing datasets in order to “train” and create an understanding of what normal operations look like. Once a period of training has taken place, the next stage is for outlier or marginal data to be highlighted in what is referred to as “anomaly detection.” This ability to detect operational events which are outside normal parameters is a key differentiator between Machine Learning and the traditional system development and coding, meaning the time between development and operational deployment can be shortened from years to months.

Our Digital Tower Laboratory inside Heathrow control tower

Working together with Searidge, our focus is on using AI and Machine Learning to support controller decision making. This might be by using it to simultaneously monitor multiple areas of interest across an airport, like runway exit points for example – something that humans aren’t capable of physically doing– in order to improve operational capability, the consistency of delivery and to enhance safety.

This ability can then be used to reduce the impact of external factors such as weather – which is what we’re trialing at Heathrow at the moment – by creating a more predictable operation in terms of aircraft spacing and runway throughput. This focus doesn’t reduce the importance of people in the process, but rather looks to support the optimisation of human performance.

One thing that was very clear from listening to other speakers was that we are in an era accelerating change, with pressure to increase the rate at which new systems can be introduced safely. Technology is going to play a huge part in the future of ATM, with AI and Machine Learning freeing people of routine tasks and allowing them to concentrate on decision making.