Generative AI-Driven Digital Twin Architecture for Urban Mobility Simulation and Decision Support

Urban mobility planning in smart cities requires sophisticated simulation tools, yet their complexity often creates a technical barrier for non-expert stakeholders. This paper presents a novel architecture that integrates generative artificial intelligence with digital twin technology to create an accessible and robust decision-support system. The framework employs a conversational AI agent based on Gemini 2.5 Flash Lite to interpret natural language intentions and translate them into validated simulation parameters. A critical safety layer, built using Pydantic, ensures that the agent’s stochastic outputs adhere to strict technical schemas and urban logic before execution. The underlying digital twin, developed with SimPy, NetworkX, and OSMnx, features a multi-source data integration strategy that includes demographic density (INE), tourism activity (ISTAC), and high-resolution traffic statistics (TomTom) to calibrate vehicle behavior. The architecture was validated through a Technology Readiness Level (TRL) 4 proof-of-concept in Las Palmas de Gran Canaria, simulating multimodal scenarios including buses, the future MetroGuagua (BRT), and pedestrian flows. Results demonstrate a 95.99% success rate in intent recognition and configuration mapping, with end-to-end execution times under 20 minutes for a 19-hour simulated day. This study demonstrates that LLM-driven orchestration, coupled with automated data pipelines and a decoupled microservice architecture, can democratize access to urban simulation, fostering more inclusive, agile, and evidence-based smart city governance.