Rangeland ecosystems provide critical wildlife habitat (e.g., greater sage grouse, pronghorn, black-footed ferret), forage for livestock, carbon sequestration, provision of water resources, and recreational opportunities. At the same time, rangelands are vulnerable to climate change, fire, and anthropogenic disturbances. The arid-semiarid climate in most rangelands fluctuates widely, impacting livestock forage availability, wildlife habitat, and water resources. Many of these changes can be subtle or evolve over long time periods, responding to climate, anthropogenic, and disturbance driving forces. To understand vegetation change, scientists from the USGS and Bureau of Land Management (BLM) developed the Rangeland Condition Monitoring Assessment and Projection (RCMAP) project. RCMAP provides robust, long-term, and floristically detailed maps of vegetation cover at yearly time-steps, a critical reference to advancing science in the BLM and assessing Landscape Health standards. RCMAP quantifies the percent cover of ten rangeland components (annual herbaceous, bare ground, herbaceous, litter, non-sagebrush shrub, perennial herbaceous, sagebrush, shrub, and tree cover and shrub height) at yearly time-steps across the western U.S. using field training data, Landsat imagery, and machine learning. We utilize an ecologically comprehensive series of field-trained, high-resolution predictions of component cover and BLM Analysis Inventory and Monitoring (AIM) data to train machine learning models predicting component cover over the Landsat time-series. This dataset enables retrospective analysis of vegetation condition, impacts of weather variation and longer-term climatic change, and understanding of vegetation treatment and altered management practice effectiveness. RCMAP data can be used to answer critical questions regarding the influence of climate change and the suitability of management practices. Component products can be downloaded https://www.mrlc.gov/data. Independent validation was our primary validation approach, consisting of field measurements of component cover at stratified-random locations. Independent validation point placement used a stratified random design, with two levels of stratified restrictions to simplify logistics of field sampling (Rigge et al. 2020, Xian et al. 2015). The first level of stratification randomly selected 15, 8 km in diameter, sites across each mapping region. First level sites excluded areas less than 30 km away from training sites and other validation sites. The second level stratification randomly placed 6–10 points within each 8 km diameter validation site (total n = 2,014 points at n = 229 sites). Only sites on public land, between 100 and 1000 m from the nearest road, and in rangeland vegetation cover within each site were considered. The random points within a site were evenly allocated to three NDVI thresholds from a leaf-on Landsat image (low, medium, and high). Sites with relatively high spatial variance within a 90 m by 90 m patch (3 × 3 Landsat pixels) were excluded to minimize plot-pixel locational error. Using NDVI as a stratum ensured plot locations were distributed across the range of validation site productivity. At each validation point, we measured component cover using the line point intercept method along 2, 30 m transects. Data were collected from the first hit perspective.