Zonation of Flood Susceptibility and Determining the Factors Affecting it Using the Maximum Entropy Method

Karaj dam basin in Alborz province is prone to destructive floods given to its special topographic and anthropogenic conditions. The purpose of this study is to determine the areas with flood susceptibility potential and prioritize the factors affecting it using the maximum entropy method. 14 factors affecting flood potential selection and linear testing Factors were analyzed by variance inflation factor. Out of a total of 47 flood points, 70 percent were randomly classified as training data and 30 percent as validation data. The Jackknife test was also used to determine the important factors. The ROC curve was used to predict the model. The results showed that there is no alignment between the factors used and therefore all factors were used in the modeling process. The results showed that according to the Jackknife test, DEM, distance from the stream and rainfall were the most important factors affecting the susceptibility of floods, respectively. Based on the area under the curve and ROC diagram, the accuracy of the model prediction was higher in the higher training sector (0.925) and good in the accreditation sector (0.717). According to the final flood susceptibility map, 22.41 percent of the study area has a moderate to high flood susceptibility potential.