An AI-Driven Spatiotemporal Crowd Orchestration Platform for Large-Scale Theme Parks: Hybrid Machine Learning, Behavioural Modelling, and Real-Time Decisioning for Safe and Efficient Guest Flow

Abstract

This paper describes an AI-based spatiotemporal crowd coordination system that can be used in large theme parks. The system relies on machine learning, behavior modeling, and real-time decision rules to forecast congestion and direct the flow of guests as well as keep the density safe. It processes real-time signals like entry surges, attraction queues and movement of pathways to predict the formation of the hotspots. The outcomes of the actual implementations indicate a 32-47 percent congestion decrease, 28 percent queue stability, and adherence to social-distancing thresholds when at peak times. The system enhances safety, flow efficiency and general guest experience providing a model that can be used elsewhere in high-density public areas.