RNN-CNN Hybrid Model to Predict C-ATC CAPACITY Regulations for En-Route Traffic

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