Resumen
Meeting the demand with the available airspace capacity is one of the most challenging problems faced by Air Traffic Management. Nowadays, this collaborative Demand?Capacity Balancing process often ends up enforcing Air Traffic Flow Management regulations when capacity cannot be adjusted. This process to decide if a regulation is needed is time consuming and relies heavily on human knowledge. This article studies three different Air Traffic Management frameworks aiming to improve the cost-efficiency for Flow Manager Positions and Network Manager operators when facing the detection of regulations. For this purpose, two already tested Deep Learning models are combined, creating different hybrid models. A Recurrent Neural Network is used to process scalar variables to extract the overall airspace characteristics, and a Convolutional Neural Network is used to process artificial images exhibiting the specific airspace configuration. The models are validated using historical data from two of the most regulated European regions, resulting in a novel framework that could be used across Air Traffic Control centers. For the best hybrid model, using a cascade architecture, an average accuracy of 88.45% is obtained, with an average recall of 92.16%, and an average precision of 86.85%, across different traffic volumes. Moreover, two different techniques for model explainability are used to provide a theoretical understanding of its behavior and understand the reasons behind the predictions.