The rapid proliferation of data centers has introduced localized environmental stressors—including episodic air pollutant emissions, waste heat, and intensive resource consumption—that may adversely affect community health. Current assessment approaches rely largely on coarse regional averages and fragmented datasets, which fail to capture neighborhood-scale, time-varying exposure patterns associated with data center operations. As a result, there is a critical need for fine-scale, integrated assessment frameworks to support rigorous health impact evaluation.
This project addresses this gap by developing a scalable, digital twin–enabled data fusion framework that integrates satellite observations, high-resolution meteorological model outputs, air quality sensor networks, land-cover and infrastructure footprint data, and geocoded demographic and health indicators. Spatiotemporal AI/ML models will support downscaling, calibration, gap filling, and uncertainty quantification within a cloud-based, reproducible workflow architecture.
Project deliverables include harmonized exposure–health datasets, interactive decision-support dashboards, and peer-reviewed publications. Collectively, these outputs will provide a rigorous, evidence-based foundation for assessing health impacts associated with data center operations, enabling data-driven planning, zoning, construction, and public health decision-making. In addition, the project advances digital infrastructure analytics, strengthens cyberinfrastructure capabilities, and generates actionable insights to support sustainable data center development and community health protection.