Polycyclic aromatic hydrocarbons (PAHs) are key atmospheric pollutants with significant carcinogenic potential that pose serious environmental and public health challenges due to their wide distribution and complex sources. In the atmosphere, PAHs exist in both gas and particle phases, with their concentrations and distributions influenced by atmospheric pollutants and meteorological conditions. This study systematically analyzed urban atmospheric PAHs using high-resolution spatiotemporal sampling data obtained from long-term monitoring. By integrating major atmospheric pollutants and meteorological parameters, spatiotemporal variations, potential sources, and complex environmental interactions of PAHs were comprehensively explored. Advanced machine learning algorithms and statistical methods were employed to identify the key factors driving PAH concentration changes and to reveal nonlinear associations with meteorological conditions and pollution sources. The results indicated significant seasonal and spatial variations in PAH concentrations, highlighting the influence of specific meteorological factors such as temperature, wind speed, and atmospheric pressure. Furthermore, the optimization of clustering and association rule mining algorithms allowed for more precise identification of emission sources and their interactions with environmental variables. These findings provide a novel perspective on the dynamic behavior of PAHs and contribute to a comprehensive understanding of their spatiotemporal distribution, sources, and environmental interactions. This study offers valuable insights for developing effective pollution control strategies, optimizing urban air quality management, and mitigating public health risks associated with PAHs exposure.