Gully erosion is a severe form of soil erosion that results in a wide range of environmental problems such as dams’ sedimentation, destruction of transportation and energy transmission lines, decreasing and losing farmland productivity, and land degradation. The main objective of this study was to map the areas prone to gully erosion, by using Frequency Ratio (FR) and random forest (RF) models. Moreover; multi- collinearity analysis was applied and 13 variables among 15 conditioning factors were selected to train the models for gully erosion susceptibility mapping (GESM). The conditioning factors include altitude, slope, aspect, plan curvature, profile curvature, drainage density, topographic wet index, precipitation, normalized difference vegetation index, land use/land cover, distance from the stream, distance from road, and soil-related variables. Model prediction potential was evaluated using the area under the curve (AUC) method. The RF model produced a higher accuracy with area under curve (AUC) an accuracy value of 89% and FR model prediction accuracy value was 77%. A detailed accuracy assessment using the Receiver Operator Characteristics (ROC) validation showed that the RF model is a reliable and accurate method for GESM than the FR model. Therefore, the RF model is useful in GESM and helps decision-makers in land-use planning and management. The outcome of this study can help managers in Aba Gerima to identify gully erosionprone areas which will help them to mitigate the gully erosion problem and prevent future gully erosion by taking preventive measures.