Abstract
Abstract. The prediction of species distribution has become a focus in ecology. For predicting a result more effectively and accurately, some novel methods have been proposed recently, like support vector machine (SVM) and maximum entropy (MAXENT). However, high complexity in the forest, like that in Taiwan, will make the modeling become even harder. In this study, we aim to explore which method is more applicable to species distribution modeling in the complex forest. Castanopsis carlesii (long-leaf chinkapin, LLC), growing widely in Taiwan, was chosen as the target species because its seeds are an important food source for animals. We overlaid the tree samples on the layers of altitude, slope, aspect, terrain position, and vegetation index derived from SOPT-5 images, and developed three models, MAXENT, SVM, and decision tree (DT), to predict the potential habitat of LLCs. We evaluated these models by two sets of independent samples in different site and the effect on the complexity of forest by changing the background sample size (BSZ). In the forest with low complex (small BSZ), the accuracies of SVM (kappa = 0.87) and DT (0.86) models were slightly higher than that of MAXENT (0.84). In the more complex situation (large BSZ), MAXENT kept high kappa value (0.85), whereas SVM (0.61) and DT (0.57) models dropped significantly due to limiting the habitat close to samples. Therefore, MAXENT model was more applicable to predict species’ potential habitat in the complex forest; whereas SVM and DT models would tend to underestimate the potential habitat of LLCs.
Highlights
The prediction of species’ distribution and potential habitat has been implemented widely and become a focus in ecology (Miller et al, 2004)
maximum entropy (MAXENT) will take the accuracies of both target and background samples into account; whereas support vector machine (SVM) and decision tree (DT) will tend to raise the accuracies of background samples, thereby reducing the accuracies of target samples and overall accuracies
For SVM, it will project the feature space to higher dimension to split the dataset in the HB case, it will pick out the area environmentally more similar to the existed samples
Summary
The prediction of species’ distribution and potential habitat has been implemented widely and become a focus in ecology (Miller et al, 2004). With the innovations of remote sensing (RS) and geographic information system (GIS) tools and statistical techniques, the predictive capability of models is substantially increasing and the models can be used to classify the dataset in more detail, like the classification of similar tree species (Dalponte et al, 2008). Few of them were devoted to classify the species in a complex forest, like the forests in Taiwan. Many species in a complex forest have the biophysiological characteristics so similar that they are difficult to discriminate. The competition among species will result in that a species might be absence in its suitable habitat so that hard to predict precisely. To classify the species accurately, we must consider about the elements in modeling, including predictive variables, quality of data, statistical methods, and so on (Guisan and Zimmermann, 2000). In terms of statistical methods, each method was developed from different principles on each scientific field, like entropy, regression, or envelope, and they will generate different results that can be used in different applications, like economic, demography, or ecology, or different level, like different scale
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
