This paper presents the outcomes of a study that utilised predictive methods based on advanced synthetic aperture radar and multispectral data coupled with Google Earth Engine to develop a model for particular TSFs based on historical records, observations, and material types. Google Earth Engine brings the first opportunity to use a systematic and comprehensive combination of radar and visual-infrared satellite data. It was found that the synergy between the two data types could be used to offset the individual ambiguities of each, and the resulting method delivered a predictive dryness probability map and visual moisture/water depth/presence indicators that were able to be verified and made operational almost immediately. On-ground visual records and aerial imagery provided qualitative verification of the approach. The methodology allows TSF operators a free, open source platform with which to monitor and map surface moisture, enabling proactive deposition decision-making to mitigate the risk of tailings dusting. Additional benefits realised include increased data on beach formation, channel and pond location (extent and to some degree depth), improving the accuracy of the TSF water balance. For the particular TSFs studied, the water balance is a critical control from a safety perspective to mitigate potential failure mechanisms, and from an operational perspective to maximise tailings density and water return to the plant.