The contemporary aviation system demands intelligent airspace capacity assessment and traffic prediction, which are essential towards maximizing operational efficiency, safety, and strategic planning. But there are few studies that combine predictive learning with complex fuzzy decision-making, and all three, which are nonlinear traffic dynamics, complex-valued expert uncertainty, and complex decision-making. To overcome uncertainty, vagueness, and complex expertise evaluations that are part of airspace management, this paper suggests a new hybrid framework that integrates both neural networks and the Complex Pythagorean Fuzzy Faire Un Choix Adequat (CPyF-FUCA) multicriteria decision-making (MCDM) model. A case study of a number of decision-makers, fifteen alternatives, and seven criteria of evaluation is conducted in order to demonstrate the practicability of the proposed methodology. In contrast to the current CPyF-based and traditional methods of MCDM, the suggested model combines neural network-based traffic prediction with CPyF-FUCA ranking of intelligent airspace consideration. The CPyF-FUCA method works well in the synthesis of expert views, fuzzy and finer-grained details of interactions, and gives some credible and explainable rankings. The sensitivity analysis and comparison analysis indicate that the proposed technique is stronger, more selective, and more reliable compared to the existing techniques based on CPyF and classical MCDM. The results could be invaluable to the air traffic officials and managers, as they will have the ability to maximize capacity, forecast traffic, and make strategic decisions. This paper is a pioneering hybrid implementation of neural networks and CPyF-FUCA in the airspace capacity assessment and traffic prediction, and provides a versatile and scalable intelligent airspace management instrument during unpredictable circumstances.
Huo et al. (Fri,) studied this question.