Architecting urban epidemic defense: A hierarchical region-individual control framework for optimizing large-scale individual mobility interventions

Abstract

In urban areas, high population density and extensive mobility can foster rapid transmission of emerging infectious diseases, particularly acute respiratory infections, which could lead to significant public health challenges and widespread social impact. EPidemic Control (EPC) strategies like mobility interventions tailored for each individual effectively mitigate these risks, balancing the safeguarding of public health with the socio-economic impacts. However, a large number of urban residents (e.g., millions) with complex spatiotemporal activities in modern cities pose a large-scale challenge of optimizing mobility interventions at an individual-level. To address this issue, this study introduces a framework of Hierarchical Region-Individual Control for Epidemic (Hi-RICE) to dynamically adapt specific interventions to large-scale individuals in complex urban epidemic scenarios with given control objectives. Hi-RICE initially assesses the dynamic infectious risk and contact risk for each individual according to their spatiotemporal behaviors. Subsequently, regional control agents, utilizing multi-agent reinforcement learning, optimize the appropriate intervention intensity for each region. Finally, specific mobility interventions are applied to high-risk individuals in each region according to their optimized control intensities. Utilizing Shenzhen, China, as a case of a megacity, simulations validate the proposed framework’s effectiveness and adaptability across various epidemic conditions, demonstrating its capacity to optimally balance epidemic control and socio-economic sustainability.