The fusion of multi-source data is essential for a comprehensive analysis of geographic applications. Due to distinct data structures, the fusion process tends to encounter technical difficulties in preserving the intactness of each source data. Furthermore, a generalized method is required to apply to what is being processed in multiple resolutions, sizes, or scales of raster and vector data. In this study, we propose a general algorithm for assigning features from raster data (concentrations of air pollutants) to vector components (roads represented by edges) in city maps through the iterative construction of virtual layers to expand geolocation from a city center to boundaries in a 2D projected map. The construction follows the rule of perfect squares with a slight difference depending on the oddness or evenness of the ratio of city size to raster resolution. We demonstrate the algorithm by applying it to assign accurate concentrations of PM2.5 and NO2 to roads in 1692 cities around the world for a potential graph-based pollution analysis. This algorithm could pave the way for agile studies on urgent climate issues by providing a generic and efficient method to fuse multiple raster and vector datasets of varying compositions.