Hosted by the Program on Chinese Cities （PCC）
11/20/2025 6:00 PM-8:00 PM EST
Presenter: Jingjing Zhang
Associate Professor, Institute of Urban Safety and Environmental Science, Beijing Academy of Science and Technology (BJAST)
Visiting scholar, University of North Carolina at Chapel Hill
Supervisor: Prof. Yan Song
Abstract:
As urbanization accelerates and air pollution becomes increasingly complex, urban environmental governance faces mounting demands for intelligent and fine-grained management. Air pollution poses a global threat to human health and sustainable development, contributing to an estimated seven million premature deaths annually (WHO). To address this challenge, a multi-scenario framework is proposed for intelligent air-quality perception and decision-making, enabling real-time detection, source identification, and adaptive regulation of complex air pollutants across urban-to-indoor scales. Building on this foundation, a data-driven methodological system is developed, centered on source attribution, adaptive monitoring, intelligent control, and predictive planning, thereby forming an intelligent governance loop that supports data-fusion- and model-driven environmental management. The core innovation integrates in-situ sensing data, source behaviors, multi-source emission dynamics, and emission contribution modeling, establishing a quantitative framework for pollution-source characterization and attribution. This integration links environmental signal recognition with responsibility assessment, enabling traceable and targeted pollution control. A digital-twin-based predictive and decision-support model further enables dynamic optimization and proactive regulation of environmental quality through visualization, behavioral feedback, and scenario evaluation. The model forecasts pollution dynamics prior to interventions, advancing strategic optimization, risk prevention, and cost efficiency. In summary, this research provides a data-driven technological foundation and intelligent governance pathway for improving environmental quality and adaptive capacity in multi-scenario smart-city systems.