My research program is centered on the mechanistic understanding of air pollution dynamics in complex environments, with a particular emphasis on the synergistic interactions between particulate matter (PM2.5) and tropospheric ozone. My work leverages a multidisciplinary framework that integrates multi-source environmental data—including in-situ monitoring, satellite remote sensing, and numerical model outputs—with advanced statistical learning and geospatial analysis. A principal objective is the development of novel, physics-informed machine learning models to overcome the limitations of sparse monitoring networks, thereby enabling high-fidelity spatiotemporal reconstruction of pollutant fields over topographically diverse regions.
My research program is centered on the mechanistic understanding of air pollution dynamics in complex environments, with a particular emphasis on the synergistic interactions between particulate matter (PM2.5) and tropospheric ozone. My work leverages a multidisciplinary framework that integrates multi-source environmental data—including in-situ monitoring, satellite remote sensing, and numerical model outputs—with advanced statistical learning and geospatial analysis. A principal objective is the development of novel, physics-informed machine learning models to overcome the limitations of sparse monitoring networks, thereby enabling high-fidelity spatiotemporal reconstruction of pollutant fields over topographically diverse regions.