Modeling Climate Change Effects on the Distribution of Oak Forests with Machine Learning

The present study models the effect of climate change on distribution Persian oak (Quercus brantii Lindl.) in Zagros forests, located west Iran. modeling is conducted under current and future climatic conditions by fitting machine learning method Bayesian additive regression tree (BART). For anticipation potential habitats for oak, two general circulation (GCMs) CCSM4 HADGEM2-ES representative concentration pathways (RCPs) 2.6 8.5 2050 2070 are used. mean temperature (MT) wettest quarter (bio8), solar radiation, slope precipitation month (bio13) respectively reported as most important variables modeling. results indicate that suitable habitat will significantly decrease both scenarios much 75.06% 2070. proposed brings insight into condition further projects local forests proper management protection endangered ecosystems.