Delays in air transport can be seen as the result of two independent contributions, respectively stemming from the local dynamics of each airport and from a global propagation process; yet, assessing the relative importance of these two aspects in the final behaviour of the system is a challenging task. We here propose the use of the score obtained in a classification task, performed over vectors representing the profiles of delays at each airport, as a way of assessing their identifiability. We show how Deep Learning models are able to recognise airports with high precision, thus suggesting that delays are defined more by the characteristics of each airport than by the global network effects. This identifiability is higher for large and highly connected airports, constant through years, but modulated by season and geographical location. We finally discuss some operational implications of this approach.

Complex network theory, in conjunction with metrics able to detect causality relationships from time series, has recently emerged as an effective and intuitive way of studying delay propagation in air transport. One important step in such analysis is converting the discrete set of landing events into a time series representing the average delay evolution. Most works have hitherto focused on fixed-size windows, whose size is defined based on a priori considerations. Here, we show that an optimal airport-dependent window size, which allows maximising the number of detected causality relationships, can be calculated. We further show how the macro-scale but not the micro-scale structure is modified by such a choice and how airport centrality, and hence its importance in the propagation process, is strongly affected. We finally discuss the implications of these results in terms of detecting the characteristic time scales of delay propagation.

The characterisation of delay propagation is one of the major topics of research in air transport management, due to its negative effects on the cost-efficiency, safety and environmental impact of this transportation mode. While most research works have naturally framed it as a transportation process, the successful application of network theory in neuroscience suggests a complementary approach, based on describing delay propagation as a form of information processing. This allows reconstructing propagation patterns from the dynamics of the individual elements, i.e. from the evolution observed at individual airports, without the need of additional a priori information. We here apply this framework to the analysis of delay propagation in the European airspace between 2015 and 2018, describe the evolution of the observed structure, and identify the role of individual airports in it. We further use this analysis to illustrate the limitations and challenges associated to this approach, and to sketch a roadmap of future research in this evolving topic.