• SPID is a deep reinforcement learning framework that models vertiport siting as a Markov decision process, using multi-head attention and gated recurrent units for spatiotemporal pattern capture and sequential decision-making.
• It outperforms traditional clustering and graph neural network (GNN)-based methods by up to approximately 29% in social performance metrics, while keeping the distance-based cost increase within 10%.
• The framework significantly enhances solution efficiency and robustness under flight range and service capacity constraints, enabling end-to-end optimization of the capacitated facility location problem.
• SPID provides a scalable and efficient approach for rapid decision-making in large-scale urban air mobility (UAM) scenarios, balancing construction costs, service levels, and social considerations.