Subjective Air Traffic Complexity Estimation Using Artificial Neural Networks

Abstract

Air traffic complexity is usually defined as difficulty of monitoring and managing a specific air traffic situation. Since it is a psychological construct, best measure of complexity is that given by air traffic controllers. However, there is a need to make a method for complexity estimation which can be used without constant controller input. So far, mostly linear models were used. Here, the possibility of using artificial neural networks for complexity estimation is explored. Genetic algorithm has been used to search for the best artificial neural network configuration. The conclusion is that the artificial neural networks perform as well as linear models and that the remaining error in complexity estimation can only be explained as inter-rater or intra-rater unreliability. One advantage of artificial neural networks in comparison to linear models is that the data do not have to be filtered based on the concept of operations (conventional vs. trajectory-based).

Determining Air Traffic Complexity – Challenges and Future Development

“…Andraši et al [36] proved that artificial neural networks (ANNs) can be used to determine air traffic complexity with the accuracy similar to the linear models. They conducted the human-in-theloop experiments with licenced air traffic controllers and concluded that the remaining variance in subjective complexity scores cannot be explained by traffic characteristics.…”

“…Whether it is a purely mathematical model that does not take into account the controllers' assessment of complexity [22] or a fully human in-theloop testing with linear regression and artificial networks [25,36], the problem of adequate complexity determination is still present. As traffic increases every year, the complexity determination will become even more important since it influences the controller's workload and airspace capacity.…”

“…Whether it is the lack of data gathered for the machine-learning [35] or artificial networks [34], or it is simply that some models are tied to the specific airspace or to the exact personnel on whom they were tested, all this makes the model unusable for adequate complexity determination when trying to use it on different airspace and other ATCO personnel [16,25]. Finally, there is a problem of inconsistent complexity assessment by the controllers when the same controller assesses different levels of traffic complexity with the same score of complexity [36].…”

“…Andraši [36] reported inconsistency when air traffic controllers assess air traffic complexity. The problem with inconsistency appears when the same controller grades the traffic situation that has a different complexity level with the same complexity scores.…”

Air Traffic Complexity as a Source of Risk in ATM

“…This indicates that there is some variation in subjective complexity scores provided by ATCOs that cannot be explained by traffic properties. Indeed, it might be the case that ATCOs introduce a degree of noise into the complexity scores due to difficulty of maintaining the consistent scoring criteria [40].…”