Ground-measured PM concentration data are oftentimes used as a response variable in various satellite-based PM mapping practices, yet few studies have attempted to incorporate ground-measured PM data collected from nearby stations or previous days as a priori information to improve the accuracy of gridded PM mapping. In this study, Gaussian kernel-based interpolators were developed to estimate prior PM information at each grid using neighboring PM observations in space and time. The estimated prior PM information and other factors such as aerosol optical depth (AOD) and meteorological conditions were incorporated into random forest regression models as essential predictor variables for more accurate PM mapping. The results of our case study in eastern China indicate that the inclusion of ground-based PM neighborhood information can significantly improve PM concentration mapping accuracy, yielding an increase of out-of-sample cross validation R by 0.23 (from 0.63 to 0.86) and a reduction of RMSE by 7.72 (from 19.63 to 11.91) μg/m. In terms of the estimated relative importance of predictors, the PM neighborhood information played a more critical role than AOD in PM predictions. Compared with the temporal PM neighborhood term, the spatially neighboring PM term has an even larger potential to improve the final PM prediction accuracy. Additionally, a more robust and straightforward PM predictive framework was established by screening and removing the least important predictor stepwise from each modeling trial toward the final optimization. Overall, our results fully confirmed the positive effects of ground-based PM information over spatiotemporally neighboring space on the holistic PM mapping accuracy.