Declining populations of Zizania palustris L. (northern wildrice, or wildrice) during the last century drives the demand for new and innovative techniques to support monitoring of this culturally and ecologically significant crop wild relative. We trained three wildrice detection models in R and Google Earth Engine using data from annual aquatic vegetation surveys in northern Minnesota. Three different training datasets, varying in the definition of wildrice presence, were combined with Landsat 8 Operational Land Imager (OLI) and Sentinel-1 C-band synthetic aperture radar (SAR) imagery to map wildrice in 2015 using random forests. Spectral predictors were derived from phenologically important time periods of emergence (June–July) and peak harvest (August–September). The range of the Vertical Vertical (VV) polarization between the two time periods was consistently the top predictor. Model outputs were evaluated using both point and area-based validation (polygon). While all models performed well in the point validation with percent correctly classified ranging from 83.8% to 91.1%, we found polygon validation necessary to comprehensively assess wildrice detection accuracy. Our practical approach highlights a variety of applications that can be applied to guide field excursions and estimate the extent of occurrence at landscape scales. Further testing and validation of the methods we present may support multiyear monitoring which is foundational for the preservation of wildrice for future generations.

Using imaging spectroscopy (hyperspectral imaging), we assessed the effects of spatial resolution, size of mapping windows composed of pixels, and number of clustered spectral species on the capacity to map plant beta diversity using the biodivMapR package, in support of the planned NASA Surface Biology and Geology (SBG) satellite remote sensing mission. Specifically, we tested the ability of biodivMapR to distinguish natural communities among field‐verified locations. biodivMapR clusters pixels as spectral species used to calculate beta diversity among mapping windows composed of multiple pixels. We used NEON airborne 1 m resolution hyperspectral images collected at three sites representing native longleaf pine ecosystems in the southeastern U.S. and aggregated pixels to 1–90 m spatial resolution for comparative analyses. We also varied mapping window size using 30 m resolution images, commonly collected by satellite missions. The capacity to detect plant beta diversity decreased with coarser spatial resolution, which corresponded to fewer pixels per mapping window. Mapping window size in turn limited the spatial resolution of beta diversity maps composed of mapping windows. Assigning too few pixels per window, as well as assigning too many spectral species per image, results in overestimation of dissimilarity among locations representing the same community type and reduces the information content of beta diversity maps. These results demonstrate the advantage of maximizing spatial resolution of hyperspectral imaging instruments on the anticipated NASA SBG satellite mission and similar remote sensing projects, as well as the value of satellite‐borne hyperspectral imagers for mapping beta diversity worldwide.