Plant productivity, forage availability and soil carbon dynamics are all strongly controlled by soil water in semi-arid rangelands. Sagebrush steppe ecosystems are among the most extensive in the western USA. We used the soil ecohydrology model (SEM) to simulate soil water dynamics and estimate plant growth at three different sagebrush steppe sites. SEM is a capacitance parameter model that uses a water balance approach to simulate daily changes in soil water and a modification of the de Wit equation to estimate plant yield. Model-simulated soil water results were evaluated using long-term (27-34years) measured data. We found that SEM accurately simulated soil water dynamics and total soil water storage at all three sites, with R-2 values greater than 0.8, Nash-Sutcliffe efficiencies near 0.8 and mean absolute errors of about 1.5cm. Model-estimated yield indices indicated a high degree of interannual variability, with values ranging more than fivefold and no long-term trend in plant production due to water availability. We also found that seasonal yield could be estimated with reasonable accuracy at the outset of the growing season (March 1) for about half of the years simulated due to either relatively high or low pre-growing season precipitation. Published 2015. This article is a U.S. Government work and is in the public domain in the USA. Ecohydrology published by John Wiley & Sons, Ltd.