Airlines are now in demand more than ever. Fed by data on everything, computers are learning how everyday life influences demand flights. In its most advanced form, AI blows up the arcane airfare codes and pricing brands that have straight-jacketed ticket sales for decades. 

By weighing up the data, technology providers can determine how much passengers will pay for tickets and continuously reprice seats. In their conversation with Bloomberg, an Israeli startup Fetcherr which operates a live-pricing engine, stated that calculating fares using AI can lift an airline’s revenue by 10% or more.

Influence of COVID-19 

Travel evaporated in 2020 as governments worldwide closed borders and rolled out COVID-19 restrictions. According to International Air Transport Association, a recovery from the pandemic should drive global airline revenue to $782 billion in 2022, still shy of the $838 billion in 2019. Typical annual revenue growth has been in the single digits since the financial crisis more than a decade ago. 

Airlines have for years used software to manage airfares. What passengers ultimately pay has been governed to some degree by seat availability in various price brackets. AI seeks to match fares more closely to passengers’ desire to pay, which has become tougher to pinpoint after two years of lockdowns.  

The influence of AI on aviation is in its infancy. However, the information flows are already too large to grasp sensibly. Fetcher alone processes multiple petabytes of data from worldwide every second as it sizes up travel demand. A single petabyte equates to 500 billion pages of standard printed text.  

ATM, FMS and ATC 

More and more companies and airports worldwide are beginning to realize that AI in aviation has some significant benefits. As it happens, tasks like flight planning, flow management, and safety assessment can be, at least to some extent, automated.  

With big data, aviation companies can train their ML algorithms to take various variables and data sources into consideration. This way, intelligent ATM applications can take weather conditions and air traffic into consideration and make appropriate decisions based on these two critical data sources.  

ML can make algorithms more and more effective over time. After initial training, they get better at operating in real-life conditions.  

When it comes to air traffic control, the main objective is to keep everyone safe. Therefore, ATC is typically managed from the control tower, where dozens of ATC specialists guide and communicate with the nearby planes and their landing and taking off. 

With ML on board, the job of ATC specialists is massively simplified. One of the companies working on such AI-fueled ATC systems is Swedish LFV. They collaborated with IBM to create an ATC system came, Advanced auto planner. Currently, they have the first proof-of-concept, a model that provides air traffic control instructions in a Swedish en route sector.  

Other applications 

AI has two primary purposes: to reduce cost and to improve efficiency. AI has made several time-consuming and previously manual jobs smart and hassle-free. This includes delay predictions, flight optimization, crew scheduling, and predictive maintenance.  

To sum up, AI in aviation is a fascinating and continuously developing field of expertise. We expect many more amazing applications in commercial airlines, air forces and vehicles. For example, airlines and carriers can optimize their routes, save time, and improve UX using AI.