AbstractSite-occupancy models that predict habitat suitability for plant species in relation to measurable environmental factors can be useful for conservation planning. Such models can be derived from large-scale presence–absence datasets on the basis of environmental observations or, where only floristic data are available, using plant trait values averaged across a plot. However, the estimated modelled relationship between species presence and environmental variables depends on the type of statistical model adopted and hence can introduce additional uncertainty. Authors used an ensemble-modelling approach to constrain and quantify the uncertainty because of the choice of statistical model, applying generalised linear models (GLM), generalised additive models (GAM), and multivariate adaptive regression splines (MARS). Niche models were derived for over 1000 species of vascular plants, bryophytes and lichens, representing a large proportion of the British flora and many species occurring in continental E...