Short-range endemic plants often have edaphic specializations that, with their restricted distributions, expose them to increased risk of anthropogenic extinction. Here, we present a modeling approach to understand habitat suitability for Ricinocarpos brevis R.J.F.Hend. & Mollemans (Euphorbiaceae), a threatened shrub confined to three isolated populations in the semi-arid south-west of Western Australia. The model is a maximum entropy species distribution projection constructed on the basis of physical soil characteristics and geomorphology data at approximately 25 m(2) (1 arc-second) resolution. The model predicts the species to occur on shallow, low bulk density soils that are located high in the landscape. The model shows high affinity (72.1% average likelihood of occurrence) for the known populations of R. brevis, as well as identifying likely locations that are not currently known to support the species. There was a strong relationship between the likelihood of R. brevis occurrence and soil moisture content that the model estimated at a depth of 20 cm. We advocate that our approach should be standardized using publicly available data to generate testable hypotheses for the distribution and conservation management of short-range endemic plant species for all of continental Australia.