Exécution de notre outil de synthèse sur un nouvel article

Résumé : The evolution of urban landscapes has sparked interest in leveraging the skyways for alleviating terrestrial traffic congestion. This paper proposes a novel computational framework to optimize Urban Air Mobility (UAM) operations by harnessing the power of parallel computing and machine learning. Utilizing methodologies like OpenMP, MPI, CUDA, and deep learning, the framework facilitates real-time traffic flow modeling, route optimization, and operational efficiency for aerial transportation systems. The results reveal a substantial enhancement in the UAM performance, showcasing a promising trajectory towards the integration of aerial networks in urban transportation systems.