There has been much excitement and activity in recent years related to the relatively sudden availability of earth-related data and the computational capabilities to visualize and analyze these data. Despite the increased ability to collect and store large volumes of data, few individual data sets exist that provide both the requisite spatial and temporal observational frequency for many urban and/or regional-scale applications. The motivating view of this paper, however, is that the relative temporal richness of one data set can be leveraged with the relative spatial richness of another to fill in the gaps. We also note that any single interpolation technique has advantages and disadvantages. Particularly when focusing on the spatial or on the temporal dimension, this means that different techniques are more appropriate than others for specific types of data. We therefore propose a space- time interpolation approach whereby two interpolation methods â€“ one for the temporal and one for the spatial dimension â€“ are used in tandem in order to maximize the quality of the result. We call our ensemble approach the Space-Time Interpolation Environment (STIE). The primary steps within this environment include a spatial interpolator, a time-step processor, and a calibration step that enforces phenomenon-related behavioral constraints. The specific interpolation techniques used within the STIE can be chosen on the basis of suitability for the data and application at hand. In the current paper, we describe STIE conceptually including the structure of the data inputs and output, details of the primary steps (the STIE processors), and the mechanism for coordinating the data and the 1 processors. We then describe a case study focusing on urban land cover in Phoenix Arizona. Our empirical results show that STIE was effective as a space-time interpolator for urban land cover with an accuracy of 85.2% and furthermore that it was more effective than a single technique.