Predicting of Areas with Ecotourism Capability Using Artificial Neural Network

Recreational use of the area must be performed conforms to its ecological capability. Therefore, this study was carried out with the aim of providing a method for modelling and ranking the areas with ecotourism capability. For this purpose, Makhdoum systemic method, regarding to the region specifications, and multi-layer perceptron artificial neural network (MLP) were used to evaluate the ecological capability of Arasbaran protected area. At first, ecological and socio-economic resources were identified and maps of them were provided. Then, ecotourism capability map was prepared by analyzing and overlaying of data in ArcGIS. In the next step, using the results of the systemic method, neural network was trained and its various structures were evaluated. Finally, map of the suitable tourism areas was modeled based on neural network output. In the end, using the socio-economic criteria and recreational attractions, prioritize and final evaluation was performed. Regarding to the systemic analysis, the area has the capability for intensive recreation class-2 (0.06%), and extensive recreation class-2 (10.33%). Topology 7-9-3 was selected as the best classifier with an overall accuracy of 98% for recreational regions classification. The best and the lowest of neural network application were shown to belong to intensive recreation class, and extensive recreation class, respectively. Based on modeled map, 0.17%, 10.09%, and 89.74% of the area were shown to belong to intensive recreation-class 2, extensive recreation-class 2, and unsuitable for recreation, respectively. This study showed artificial neural network has potential for classification of the suitable tourism areas with high accuracy.