Fine particle matter (PM_2.5) significantly affects the atmospheric environment and human health. The satellite-derived aerosol optical depth (AOD), which could represent the concentration of atmospheric particles to a certain extent, is widely used for estimating ambient PM_2.5 concentration, in combination with diverse auxiliary information. However, the general satellite-derived PM_2.5 products exhibit limitation in the application and aggregate analysis of PM_2.5 in urban areas, because of the moderate spatial resolution to match the urban landscape and low spatial coverage making it hard to describe airmass trajectory. In order to explore the potential application value of PM_2.5 concentration products with relatively high spatial coverage and resolution, a two-stage machine learning and geo-statistics coupled model incorporating with a feedback mechanism was proposed in this study. To be specific, we firstly develop a hybrid back-propagation neural network coupled kriging with external drifting approach (BPNN-KED) for estimating 1-km daily PM_2.5 concentration maps at high coverage over four urban agglomerations in China. The model performs well, with R² up to 0.83 and root mean square error of 14.7 μg/m³ from cross-validation. The daily PM_2.5 maps display an average spatial coverage exceeding 95%, and on an average, each grid produces 350 days of valid estimations annually. In addition, the extra value of the high-coverage PM_2.5 estimates were explored through the more accurate aggregate analysis of urban PM_2.5 pollution level. The advantage of the high-coverage PM_2.5 estimation is demonstrated through daily PM_2.5 hotspot identification over urban areas, providing substantially fine spatially resolved PM_2.5 trends, which offers the potential for daily pollutant emission sources location through satellite remote sensing technology. Moreover, the spatiotemporally continuous PM_2.5 concentrations possess the ability to capture polluted air mass trajectories, thereby offering observational support not only for evaluating the contribution from exogenous pollutants to local PM_2.5 concentrations and but also for providing empirical references for haze warning.