Towards resilient cities: A hybrid simulation framework for risk mitigation through data-driven decision making
🤖 AI Summary
Existing urban risk management systems suffer from incomplete coverage, insufficient coupling of heterogeneous operational data sources, and the absence of unified evaluation criteria. To address these challenges, this study proposes a hybrid simulation-based decision support framework integrating physics-informed modeling with data-driven methodologies. The framework introduces an innovative multi-scale coupled simulation architecture that enables real-time co-modeling of infrastructure network dynamics and socio-behavioral data. It synergistically integrates system dynamics, graph neural networks, Bayesian optimization, and digital twin technologies to support closed-loop decision-making for risk identification, propagation simulation, and resilience enhancement. Validated across three pilot cities, the framework achieves a 42% reduction in disaster response latency and a 31% decrease in recovery time for critical infrastructure. This work establishes a scalable, interpretable, and quantitatively evaluable technical paradigm for risk governance in complex urban systems.
Application Category
Problem
Research questions and friction points this paper is trying to address.
Urban Risk Management
Decision Support System
Interconnected Affairs
Innovation
Methods, ideas, or system contributions that make the work stand out.
Complex Systems Modeling
Hybrid Simulation Method
Resilience Assessment
🔎 Similar Papers
No similar papers found.
