Volume 9, Issue 2 (8-2020)                   2020, 9(2): 45-59 | Back to browse issues page


XML Persian Abstract Print


Isfahan University of Technology
Abstract:   (3496 Views)
Habitat degradation is one the important reasons of plant species extinction. Modeling techniques are widely used for identifying the potential habitats of different plant species. Thus, the purpose of current study was to determine potential habitats of Zalzalak in Lorestan Province. Species presence data and 23 environmental variables were collected in Lorestan Province. Correlation analysis was then applied to reduce the environmental variables into nine effective ones and potential habitat of the species was determined using five models including Maximum Entropy (MAXENT),Generalized Linear Models (GLM), Generalized Additive Models (GAM), Multivariate Adaptive Regression Splines (MARS) and Generalized Boosting Model (GBM). Models were evaluated with receiver operating characteristic (ROC) plots, true skill statistic (TSS) and Kappa coefficients. Results showed that ROC and Kappa coefficients were excellent for all models and TSS values were excellent for GBM and MAXENT, good for MARS and GAM and medium for GLM model. According to the combined model, 40% of the province was classified as suitable and 60% as unsuitable. The precipitation of the three coldest months of the year, annual rainfall and elevation were the most effective environmental variables in Zalzalak habitat mapping. The maximum presence of the species occurred at the rainfall and elevation range of 160–220 mm and 1300–1850 m, respectively. Due to the high accuracy of the Zalzalak suitable habitat map, it can be used by related organizations, as an appropriate tool for reclamation of degraded regions and conservation of current habitats.
Full-Text [PDF 1426 kb]   (1404 Downloads)    
Type of Study: Research | Subject: General

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.