In phase i research, atcorp innovatively integrated two diverse technologies bayesian networks and genetic algorithm to develop a methodology called PROCAST1 for global optimization under…

This federal contract award, valued at $769,077.10, was issued by the National Aeronautics and Space Administration (NASA) to Architecture Technology Corporation (ATC), a small business, under a Cooperative Agreement. The contract is for Phase II research and development of the PROCAST methodology, which integrates Bayesian networks and genetic algorithms to address complex optimization problems, with a focus on improving integrated arrival-departure surface air traffic management at busy metropolitan airports.

The contract tasks include enhancing PROCAST's scheduling algorithms, traffic coordination capabilities, and Bayesian network learning to support real-time decision-making. Additionally, the contract involves expanding the system's scope to a multi-airport "metroplex" environment and conducting simulation-based benefits analyses to demonstrate the viability of incorporating PROCAST into operational air traffic management research and systems. This contract award is not associated with a set-aside designation.

In phase i research, atcorp innovatively integrated two diverse technologies bayesian networks and genetic algorithm to develop a methodology called PROCAST1 for global optimization under uncertainty . Procast is generally applicable to a wide range of complex problems displaying certain characteristics. One such problem is integrated arrival departure surface air traffic management in busy metropolitan areas. In phase i we generated an iads traffic management tool for efficiently managing traffic on an airport surface and in the terminal airspace while maintaining robustness to unforeseen disturbances. We conducted proof ofconcept simulation experiments which showed that procast if applied at the john f kennedy airport would provide significant benefits over todays system. Encouraged by promising phase i results our research objective n phase II is to expand and generalize the solution to problems of greater scope, complexity and uncertainty specifically we propose to enhance procast in multiple ways we enhance procasts scheduling algorithms in three ways expand the algorithm to a multi airport scope this capability metroplex procast or mprocast add multi objective cost functions with complex modeling of primarily safety factors and other competing objectives and add sub algorithms for improved traffic coordination under severe weather rerouting and DE icing operations enhance the BNS by incorporating operational insights from our subject matter expert consultants and enable BN learning over large scale historical operational data as opposed to small scale simulation data in phase i for more accurate prediction of future traffic develop fast online BN inference methods and machine learning methods to synthesize best flight control strategies for facilitating mprocasts future infusion into a real time decision support tool enhance nasas surface simulation platform to generate a complete metroplex surface and airspace simulation capability for benefits analysis and conduct simulation based benefits analyses of mprocast and provide NASA FAA industry with credible data for evaluating viability of mprocasts infusion into their research programs processes and products