Distribution models for mountain plant species: The value of elevation

The climatic conditions of mountain habitats are greatly influenced by topography. Large differences in microclimate occur with small changes in elevation, and this complex interaction is an important determinant of mountain plant distributions. In spite of this, elevation is not often considered as a relevant predictor in species distribution models (SDMs) for mountain plants. Here, we evaluated the importance of including elevation as a predictor in SDMs for mountain plant species. We generated two sets of SDMs for each of 73 plant species that occur in the Pacific Northwest of North America; one set of models included elevation as a predictor variable and the other set did not. AUC scores indicated that omitting elevation as a predictor resulted in a negligible reduction of model performance. However, further analysis revealed that the omission of elevation resulted in large over-predictions of species' niche breadths-this effect was most pronounced for species that occupy the highest elevations. In addition, the inclusion of elevation as a predictor constrained the effects of other predictors that superficially affected the outcome of the models generated without elevation. Our results demonstrate that the inclusion of elevation as a predictor variable improves the quality of SDMs for high-elevation plant species. Because of the negligible AUC score penalty for over-predicting niche breadth, our results support the notion that AUC scores alone should not be used as a measure of model quality. More generally, our results illustrate the importance of selecting biologically relevant predictor variables when constructing SDMs.

Geochemistry and mineralogy of garnet grains from ODP Sample 183-1137A-33R-3,50-53

On Elan Bank, a southwestern promontory of the Kerguelen Plateau in the southern Indian Ocean, we cored an interval of conglomerate and minor sandstone within a thick section of Cretaceous flood basalts. Most of the detritus in these sedimentary rocks is volcanic with the exception of a small amount of conspicuous material of probable continental derivation. The anomalous clasts include several pebbles of gneiss (Nicolaysen et al., 2001, doi:10.1130/0091-7613(2001)029<0235:POPGBG>2.0.CO;2) and garnet sand grains. The presence of continental material on the plateau bears significantly on the interpretation of Indian Ocean basalts (Weis et al., 2001, doi:10.1130/0091-7613(2001)029<0147:OOCCII>2.0.CO;2). The purpose of the present study was to determine the composition of the garnets to provide additional constraints on the nature of the source area.