Can We Move Freely in NEOM's The Line? An Agent-Based Simulation of Human Mobility in a Futuristic Smart City

2025-07-20

AI Summary

This study addresses the feasibility of unconstrained human mobility within NEOM’s “The Line”—a 170-km linear city in Saudi Arabia. We propose a multi-agent simulation framework integrating reinforcement learning and graph neural networks to enable dynamic path planning and resource allocation in complex, three-dimensional transportation environments. Our method fuses synthetic data with real-world urban trajectory datasets to construct a fully AI-driven, multimodal traffic simulation system. Experimental results demonstrate an average commute time of 7.8–8.4 minutes, resident travel satisfaction of 89.2%, spatial accessibility exceeding 91.5%, and a 32.7% reduction in energy consumption and carbon emissions per kilometer compared to baseline schemes. To our knowledge, this work presents the first high-fidelity, scalable AI-powered traffic simulation for ultra-long linear cities, establishing a verifiable technical paradigm and quantitative evaluation benchmark for the design and operation of future compact linear urban systems.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This paper investigates the feasibility of human mobility in The Line, a proposed 170-kilometer linear smart city in NEOM, Saudi Arabia. To assess whether citizens can move freely within this unprecedented urban topology, we develop a hybrid simulation framework that integrates agent-based modeling, reinforcement learning, supervised learning, and graph neural networks. The simulation captures multi-modal transportation behaviors across 50 vertical levels and varying density scenarios using both synthetic data and real-world traces from high-density cities. Our experiments reveal that with the full AI-integrated architecture, agents achieved an average commute time of 7.8 to 8.4 minutes, a satisfaction rate exceeding 89 percent, and a reachability index of over 91 percent, even during peak congestion periods. Ablation studies confirmed that the removal of intelligent modules such as reinforcement learning or graph neural networks significantly degrades performance, with commute times increasing by up to 85 percent and reachability falling below 70 percent. Environmental modeling further demonstrated low energy consumption and minimal CO2 emissions when electric modes are prioritized. The findings suggest that freedom of movement is not only conceptually achievable in The Line, but also operationally realistic if supported by adaptive AI systems, sustainable infrastructure, and real-time feedback loops.

Problem

• Assess human mobility feasibility in The Line smart city
• Evaluate AI-integrated transportation performance in dense urban topology
• Analyze sustainability impact of multi-modal mobility systems

Innovation

• Hybrid simulation with agent-based and AI models
• Multi-modal transport across 50 vertical levels
• AI-integrated architecture ensures high efficiency