Quantifying Plant Species ?-Diversity Using Normalized Difference Vegetation Index and Climate Data in Alpine Grasslands

Quantitative plant species ?-diversity of grasslands at multiple spatial and temporal scales is important for investigating the responses biodiversity to global change protecting under change. Potential (i.e., SRp, Shannonp, Simpsonp Pieloup: potential richness, Shannon index, Simpson index Pielou respectively) were quantified by climate data annual temperature, precipitation radiation) actual SRa, Shannona, Simpsona Pieloua: normalized difference vegetation data. Six methods random forest, generalized boosted regression, artificial neural network, linear support vector machine recursive regression trees) used in this study. Overall, constructed forest models performed best among six algorithms. The simulated based on can explain no less than 96% variation observed ?-diversity. RMSE relative biases between ?1.58 within ±4.49%, respectively. Accordingly, be from using models. build study had enough predicting accuracies, least alpine grassland ecosystems, Tibet. proposed current help researchers save time abandoning community field surveys, facilitate conduct studies over a long-term scale larger