The past six decades has seen an explosive growth in remote sensing data across air, land, and water dramatically improving predictive capabilities of physical models and machine-learning (ML) algorithms. Physical models, however, suffer from rigid parameterization and can lead to incorrect inferences when little is known about the underlying physical process. ML models, conversely, sacrifice interpretation for enhanced predictions. Geostatistics are an attractive alternative since they do not have strong assumptions like physical models yet enable physical interpretation and uncertainty quantification. In this work, we propose a novel multiscale multi-platform geostatistical algorithm which can combine big environmental datasets observed at different spatio-temporal resolutions and over vast study domains. As a case study, we apply the proposed algorithm to combine satellite soil moisture data from Soil Moisture Active Passive (SMAP) and Soil Moisture and Ocean Salinity (SMOS) with point data from U.S Climate Reference Network (USCRN) and Soil Climate Analysis Network (SCAN) across Contiguous US for a fifteen-day period in July 2017. Using an underlying covariate-driven spatio-temporal process, the effect of dynamic and static physical controls—vegetation, rainfall, soil texture and topography—on soil moisture is quantified. We successfully validate the fused soil moisture across multiple spatial scales (point, 3 km, 25 km and 36 km) and compute five-day soil moisture forecasts across Contiguous US. The proposed algorithm is general and can be applied to fuse many other environmental variables.