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