The European Air Traffic Management Network (EATMN) is comprised of various stakeholders and actors. Accordingly, the operations within EATMN are planned up to six months ahead of target date (tactical phase). However, stochastic events and the built-in operational flexibility (robustness), along with other factors, result in demand and capacity imbalances that lead to delayed flights. The size of the EATMN and its complexity challenge the prediction of the total network delay using analytical methods or optimization approaches. We face this challenge by proposing a deep convolutional neural network (DCNN), which takes capacity regulations as the input. DCNN architecture successfully improves the prediction results by 50 percent (compared to random forest as the baseline model). In fact, the trained model on 2016 and 2017 data is able to predict 2018 with a mean absolute percentage error of 22% and 14% for the delay and delayed traffic, respectively. This study presents a method to provide more accurate situational awareness, which is a must for the topic of network resiliency.

The European Air Traffic Management Network is unique in its complexity due to numerous stakeholders, airspace configurations and accommodated traffic volumes. Such complexity challenges both tactical visibility and network resiliency in general. Therefore, we review different perspectives of resiliency and robustness to explore advantages of performance variability in understanding network states. The methodology is based on capturing emergent disruptions as drivers of performance variability. We claim that capacity regulations reveal restorative mechanisms for tactical planning. Consequently, we conduct statistical evaluations to provide quantitative measures for network state definitions. The methodology is even able to distinguish non-nominal disruptions to either crisis or critical states. The proposed approach is then demonstrated by a data sample covering six months. Furthermore, to assess the severity of non-nominal states, we estimate probability distributions for different regulation types. The study is concluded by addressing long-term network resiliency based on estimated probability distributions.