Gully erosion causes high soil erosion rates and is an environmental concern posing major risk to the sustainability of cultivated areas of the world. Gullies modify the land, shape new landforms and damage agricultural fields. Gully erosion mapping is essential to understand the mechanism, development, and evolution of gullies. In this work, a new modeling approach was employed for gully erosion susceptibility mapping (GESM) in the Golestan Dam basin of Iran. The measurements of 14 gully-erosion (GE) factors at 1042 GE locations were compiled in a spatial database. Four training data sets comprised of 100%, 75%, 50%, and 25% of the entire database were used for modeling and validation (for each data set in the common 70:30 ratio). Four machine learning models – max entropy (MaxEnt), general linear model (GLM), support vector machine (SVM), and artificial neural network (ANN) – were employed to check the usefulness of the four training scenarios. The results of random forest (RF) analysis indicated that the most important GE effective factors were distance from the stream, elevation, distance from the road, and vertical distance of the channel network (VDCN). The receiver operating characteristic (ROC) was used to validate the results. Area under the curve (AUC) values for the four training samples modeled were 100% (AUC = 0.857), 75% (AUC = 0.884), 50% (AUC = 0.904), and 25% (AUC = 0.859) respectively. These results indicate that the ANN model is highly accurate in GESM, but the 50% sample was most accurate. The other models – SVM (AUC = 0.898), GLM (AUC = 0.853) and MaxEnt (AUC = 0.841) also achieved acceptable results.