Slide Type Landslide Susceptibility Assessment of the Büyük Menderes Watershed Using Artificial Neural Network Method
Abstract The Büyük Menderes watershed is the largest drainage watershed in Western Anatolia with an area of approximately 26000 km2. In the study area, almost 863 landslides occurred, extending over 222 km2 with a mean landslide area of 0.21 km2. In this study, landslide susceptibility assessment was carried out using Artificial Neural Network method which is one of the data driven methods. Geology, digital elevation model, slope, topographic wetness index, roughness index, plan, profile curvatures, and proximity to the active faults and rivers were used as landslide conditioning factors. In susceptibility assessments, landslides were separated by 70 % analysis, 15 % test and validation data sets by random selection method. The performance of the landslide susceptibility map was assessed by the area under the receiver operating characteristic curves, error histogram, and confusion matrix, respectively. The area under the receiver operating characteristic curves, analysis, testing, validation, landslides and study ares was found 0.82, 0.84, 0.86, 0.82. The susceptibility map had a high perediction rate in which high and very high susceptible zones corresponded to 26 % of the study area including 82 % of the recorded landslides.
