Extending vegetation site data and ensemble models to predict patterns of foliage cover and species richness for plant functional groups

The training matrix (Step 2.2 in Figure 2) was created by extracting the value for each predictor surface for each site with response data, as well as every background point (see Supplementary Material S4—NN Extract from Binaries.exe for software designed to build matrices). <br>The dataset used to train the species richness models contained 6806 sites and an additional 2462 background points. <br>The dataset used to train foliage cover models contained 3021 floristic sites and we selected a random subset of 1015 background points.