Evaluation of Land Suitability for Olive (Olea europaea L.) Cultivation Using the Random Forest Algorithm

Many large dams built on the Çoruh River have resulted in inundation of olive groves Artvin Province, Turkey. This research sets out to identify suitable locations for cultivation using random forest (RF) algorithm. A total 575 plots currently listed Farmer Registration System, where is practiced, were used as inventory data training and validation RF model. In order determine areas can be carried out, a land suitability map was created by taking into account 10 parameters including average annual temperature, precipitation, slope, aspect, use capability class, sub-class, soil depth, other properties, solar radiation, cover. According this map, an area 53,994.57 hectares detected production within study region. To validate model, receiver operating characteristic (ROC) curve under ROC (AUC) utilized. As result, AUC value determined 0.978, indicating that method may successfully determining lands particular, well crop-based general.