Climate‐based approach for modeling the distribution of montane forest vegetation in Taiwan

Abstract

Aims Climate shapes forest types on our planet and also drives the differentiation of zonal vegetation at regional scale. A climate‐based ecological model may provide an effective alternative to the traditional approach for assessing limitations, thresholds, and the potential distribution of forests. The main objective of this study is to develop such a model, with a machine‐learning approach based on scale‐free climate variable estimates and classified vegetation plots, to generate a fine‐scale predicted vegetation map of Taiwan, a subtropical mountainous island. Location Taiwan. Methods A total of 3,824 plots from 13 climate‐related forest types and 57 climatic variable estimates for each plot were used to build an individual ecological niche model for each forest type with random forest (RF). A predicted vegetation map was developed through the assemblage of RF predictions for each forest type at the spatial resolution of 100 m. The accuracy of the ensemble RF model was evaluated by comparing the predicted forest type with its original classification by plot. Results The climate environment of regions higher than 100 m above sea level in Taiwan was classified into potential habitats of 13 forest types by using model predictions. The predicted vegetation map displays a distinct altitudinal zonation from subalpine to montane cloud forests, followed by the latitudinal differentiation of subtropical mountain forests in the north and tropical montane forests in the south, with an average mismatch rate of 6.59%. An elevational profile and 3D visualization demonstrate the excellence of the model in estimating a fine, precise, and topographically corresponding potential distribution of forests. Conclusions The machine‐learning approach is effective for handling a large number of variables and to provide accurate predictions. This study provides a statistical procedure integrating two sources of training data: (a) the locations of field sampling plots; and (b) their corresponding climate variable estimates, to predict the potential distribution of climate‐related forests.

Extensive sampling of Saccharomyces cerevisiae in Taiwan reveals ecology and evolution of predomesticated lineages

“…We found that, unlike the general expectation in biogeographic studies that an island only contains a subset of genetic diversity from the mainland population, the genetic diversity of S. cerevisiae populations from Taiwan can be as diverse as those found in the Asia continent. The persistence of ancestral lineages may be a result of Taiwan being a high environmentally heterogeneous region (Ali 2018;Lin et al 2020) and its prolonged bioclimatic stability (Tsukada 1966) than that of nearby eastern China. Alternatively, the geographic scale for distinguishing island and mainland populations and the importance of habitat diversity may differ between microorganisms (Davison et al 2018) and other macro-organisms, such as animals and plants.…”

Predicting suitable habitats of Melia azedarach L. in China using data mining

“…Silva et al found the highest model quality for the RF and GAM algorithms when assessing the limitations of different species distribution models using the Azorean Forest as an example 29 . The RF is an ensemble machine-learning model that could handle data with multi-dimensional, non-linear relationships, high-order correlations, and missing values 30 . Additionally, the RF model is capable of avoiding the accuracy reduction problem caused by missing and noisy data in the training sample when predicting the relationship between a large number of predictor variables and the response variable 31 , attributes supporting the present study results.…”

Integrating plot‐based and remotely sensed data to map vegetation types in a New Zealand warm‐temperate rainforest

“…Alternatively, Tapia et al (2005) introduced a confusion index calculated as the ratio between the membership values of the community with the highest prediction and that having the second highest value. Lin et al (2020) assigned predicted pixels to either the predicted forest type or to “mixed” or “uncertain”, classes based on predicted values for the 13 forest types modeled. Duff et al (2014) directly predicted the fuzzy membership value for each association mapped.…”