A machine learning model to predict runway exit at Vienna airport

Analysis of airport ground operations based on ADS-B data

“…In the context of aviation, several methods from the field of artificial intelligence are used to cluster [15]- [18], detect anomalies [19]- [22] and predict aircraft trajectories [23]- [25], develop dynamic airspace designs [26], [27], analyse runway and apron operations [21], [28]- [30], determine airport performance including the impact of local weather events [31], [32], and for airport terminal operations (turnaround) [33]. More initiatives to leverage ADS-B open data in order to improve the state of the art are already commonplace, esp.…”

“…We consequently follow a research agenda for a datadriven management of airport operations: (a) concept of a performance-based, integrated airport management [36], (b) analysis of operational scenarios to mitigate impacts of capacity restrictions [37], (c) systematic analysis of correlations between airport performance and weather conditions at European airports [38], (d) data-driven models to forecast operational delays using neural networks [31], [32], and (e) forecast of specific parts of aircraft ground trajectory [28].…”

“…Inbound trajectories determine landing times and are part of the airport arrival management to ensure an efficient use of runway capacity. After the aircraft landed, the runway occupancy time determine the further use of this particular runway, and dependent operations at other runways, for arrival and departure procedures [28].…”

Ready for digital transformation? The effect of organisational readiness, innovation, airport size and ownership on digital change at airports

“…Airports have embraced digital change, whether it is encoding analogue information into a digital format or using technologies to alter and add value to existing processes and functions. For some, change is now being driven by current or emerging technologies such as augmented reality ( Eschen, 2018 ), Big Data Analytics ( Mullan, 2019 ), blockchain ( Di Vaio and Varriale, 2020 ), cloud computing ( Amadeus, 2014 ), cognitive computing ( Herrema et al, 2019 ; Sadjadi and Jarrah, 2011 ), cybersecurity ( ACI, 2020 ), systems integration ( Stocking et al, 2009 ), the Internet of Things ( Mariani et al, 2019 ; Zmud et al, 2018 ) and virtual modelling and simulation ( Ørsted, 2019 ). These technologies allow airports to develop systems that monitor, visualise and respond to digital processes and functions in real-time, and as part of a wider ecosystem that connects all stakeholders ( Halpern et al, 2021 ).…”

Data-Driven Simulation for Evaluating the Impact of Lower Arrival Aircraft Separation on Available Airspace and Runway Capacity at Tokyo International Airport

“…In their case study, the runway capacity was estimated to be around 8 to 18% higher than the results obtained with FTS [14], as their model did not fully capture the characteristics of the constraints imposed by the airport infrastructure. In order to identify the precursors of an increase in ROT or a runway exit miss, Herrema et al (2019) [15] proposed a machine learning approach for predicting the runway exit to be used based on actual movements at the airport. The results showed that their proposed model achieved 79% accuracy rate of the decision variable which determined whether a flight rolled out runway exit following the procedure or not.…”