State and transition models (STMs) are widely used for organizing, understanding, and communicating complex information regarding ecological change. One foundational component of STMs is the representation of the current state of ecological sites (ecosites) delineated by topoedaphic features. Field inventory and assessment techniques used to characterize ecosites are labor-intensive and based on limited sampling in time and space. Remote sensing and Geographic Information System technologies increasingly offer opportunities to generate synoptic, high-resolution characterizations of ecosites in heterogeneous and remote rangelands. Here, we show how advanced remotely-sensed hyperspectral data acquired by the National Ecological Observatory Network can be combined with uncrewed aerial vehicle data within a GIS framework to quantify land cover at scales that inform STMs in Sonoran Desert landscapes in southern Arizona. Using 1 m airborne hyperspectral reflectance data, spectral vegetation and moisture indices (derived from hyperspectral bands and rendered together with the hyperspectral stack), and aerial imagery for ground-truthing, we were able to 1) produce a classification product quantifying some, but not all, plant and soil categories used in STMs and 2) delineate the spatial pattern and areal extent of ecological states on several ecological sites. Our remote sensing-based assessments were then compared to vegetation state maps based on traditional field surveys. We found that with the exception of native vs. nonnative grass ground cover, remote sensing picked up contributions of key ecostate classification variables. Remote sensing products thus have value for planning and prioritizing field surveys and pinpointing areas of concern or novelty. Furthermore, remote sensing approaches more thoroughly encompass greater spatial extents and are ostensibly more cost-effective than traditional field surveys when viewed through the lens of the time-series analyses needed to document whether the ecological states in STMs are stable or in the process or transitioning.