Airborne and satellite remote sensing can potentially be used to model crop characteristics. However, satellite imagery usually exhibit low spatial and temporal resolutions, and manned aircraft imagery, despite improved resolutions, is not cost-effective. Recent developments in UAV remote sensing have allowed for imagery at improved spatial resolutions relative to satellites and at a fraction of the cost relative to manned aircraft. Furthermore, UAVs offer potential advantages over proximal soil sensors (i.e. EM-38) in terms of in-season decision making. However, it is unclear at this point whether these benefits translate to higher quality information. This question has relevance within fields that exhibit contrasting environments, such as soil spatial variability. Therefore, the objectives of this paper were twofold: 1) to quantify improvements in UAV-based plant (cotton) modelling relative to proximal sensing (i.e. EM-38), manned aircraft, and satellites (Landsat 8); and 2) to determine how such modeling can be affected by soil spatial variability. Results indicate that UAVs show higher nugget/sill ratios and larger ranges than manned aircraft and satellites. These results have implications for predicting agronomic variables (i.e. yield, plant height), as well as soil/plant sampling.