Foliar moisture content (FMC) plays a crucial role in the arid, fire-adapted forests of the western US by influencing fire behavior, tree survival, and serving as a proxy for tree health. Management actions such as mechanical thinning and prescribed fire mitigate wildfire risk and improve forest health by reducing fuel connectivity, diversifying forest structure, and creating canopy gaps. These management actions could be improved by the targeted removal of moisture stressed trees during treatments. However, maps of FMC are not widely available at the tree-level, with no existing products to map FMC of western conifers at ultra-high resolution. This project focuses on the scalability of a laboratory-developed models of sapling FMC to develop an assess tree-level FMC in natural forest conditions. Specifically, we tested: Can existing FMC models accurately predict individual tree FMC using uncrewed aerial system (UAS) data? Field testing demonstrated that while laboratory-based models yielded low accuracies and a field-developed model only explained ~31% of the variation, the field model successfully classified trees into FMC categories (i.e. 10% lowest FMC, 90% highest FMC) with up to 89.8% accuracy. The successful classification demonstrates strong potential for UAS-based FMC mapping to inform management prescriptions. The integration of UAS-derived FMC classification into forest management decision workflows will enhance forest resilience and the adaptive capacity of managers.