Plant species distribution is a function of climatic, topographic, soil and biological factors, in which climate is among the most important variables affecting species occurernce in broad scale. planet earth. Predictive species distribution models are used to generate Nowadays, climate change as a serious challenge is threatening life in the and species presence and absence data are used in these models to identify potential distribution maps for conservation planning. The environmental variables predict potential distribution of Artemisia seiberi and Artemisia optimal environmental conditions for species occurence. This study aimed to aucheri in the current and future climatic condition under the HadGEM2-ES climatic model by 2050 and 2070. We used 19 climatic and 3 topographic variables with spatial resolution of 250 meters to record the occurrence data of the species. The relationship between occurrence produce the potential map of the species. Vegetation type map was used to points and environmental variables were determined based on Maximum Entropy Belief Networks () model in Netica program. Results of MaxEnt model showed Model (MaxEnt). Species response curves were then used to produce a Baysian elevation, slope, temperature seasonality, mean temperature of wettest quarter, and precipitation of coldest quarter as the most important variables considerably, implying on this fact that the studied species are resist to climate influencing these species distribution. Results of climate change projections showed that the extent of suitable habitat of these species will not change that the MaxEnt model identified potential habitats of the species better than change in future. The extent of suitable habitat of the species were also properly predicted by and the contribution of environmental variables in the probability of presence of the species were analyzed. Overall, regarding the spatial distribution of suitable habitat, results of this study indicated model. Keywords: Species distribution model, Geographic Information System, Baysian Belief Network, climate change.
