The Nianzhuanggou watershed of Yan’an City was regarded as the study area. Based on the field survey and remote sensing image, the data of 73 landslide points were obtained. 70% of the points were used as training dataset, and the remaining were used for validation purpose. Slope, aspect, elevation, normalized difference vegetation index (NDVI), lithology, land use, plan curvature and profile curvature were selected as explanatory variables for landslide susceptibility modeling. The landslide susceptibility index (LSI) of the study area was calculated using the index of entropy model (IOE), and a landslide susceptibility map (LSM) was generated. Finally, the results were evaluated using the accuracy and area under the receiver operating characteristic curve (AUC). The results show that the accuracy of the training dataset and the validation dataset are both greater than 0.8, and the AUC value of validation dataset is 0.964 1, indicating that the LSM is highly reliable, and the IOE model has strong generalization ability. The results can also provide some reference for the local prevention and control of landslides.