On the airport side, the Regulation Outlook AI-based predictive model provides new enhanced predictions of airport regulations using information available prior to the operations.
How it works
The airport regulations are then integrated into the Network Manager Operations Center (NMOC) up to 30 hours before the operations. Regulation Outlook AI uses information from airport events in NM’s “Airport Corner” and from NOTAMs, as well as weather and traffic forecasts to estimate the likelihood of a regulation being required at any of the network’s busiest airports. It already predicts the hours when regulations are more likely - with 84 % accuracy.
The AI models currently used, essentially deep neural networks, are of such complexity that it is practically impossible to understand their inner workings. Regulation outlook addresses concerns about “AI explainability” by providing the rationale behind the prediction, be it atmospheric phenomena, industrial action, works in progress at the airport, over demand, etc.
The results and details of the predictions are embedded in the Airport Function Dashboard, providing the Airport Function with an integrated view in pre-tactical and tactical time frames.
This information is shared with the rest of the functions in the NMOC. The purpose of the prediction is NOT to take any un-coordinated action but to pro-actively contact the airport for considering in a collaborative way the best options.
Although it was initially planned to serve as a decision support tool for the NMOC Airport Function, Regulation Outlook AI will also be shared with our stakeholders, airports and airlines to foresee the impact that airports’ daily situations have on their own operations.