The current research lacks in-depth examination of the relationship between blue-green space elements and particulate matter at the urban scale, making it difficult to clearly allocate blue-green spaces within urban planning systems. In response, this study focuses on the urban scale and selects Xiangyang, which suffers from severe particulate pollution, as the study area. Collaborating with the Xiangyang Ecological Environment Monitoring Center of Hubei Provincial Department of Ecology and Environment, a high-density near-surface monitoring sensor network for particulate matter and six meteorological elements has been actively established in the central urban area to overcome the issue of insufficient sample points provided by existing discretely distributed monitoring stations. Secondly, following the principles of particulate matter diffusion, we establish a Gaussian kernel density dataset of blue-green space elements that conforms to the spatial process of particulate matter diffusion, and then, a dual-precision nested algorithm is designed to select the best representative elements, allowing for a more refined representation of the interaction between particulate matter and blue-green space elements during the spatial diffusion process. Finally, we input the dataset as independent variables into a geographically weighted regression model to determine the range as well as the intensity of particulate matter reduction by blue-green space elements and propose their precise intervention locations. This study provides a scientific basis for creating a healthy urban living environment.