Abstract: [Objective] The southern region of Dengfeng City, Henan Province, is located in the transitional zone between the Songshan Mountains and the middle and lower reaches of the Yellow River plain. Landslides occur frequently, posing a serious threat to regional security. [Methods] This study comprehensively applies optical remote sensing and small baseline ensemble synthetic aperture radar interferometry (SBAS InSAR) technology to carry out early identification of landslide hazards, and conducts susceptibility evaluation based on information models and machine learning methods (artificial neural networks, random forests, and stacking ensemble strategies). [Results] The results showed that: (1) Through optical remote sensing interpretation and SBAS InSAR deformation monitoring, a total of 36 landslide hazard points were identified. Combined with field verification, it was confirmed that 31 of them were landslide disasters, mainly distributed in the central, southwestern, and southeastern regions. Their spatial distribution was significantly correlated with terrain slope , rock weak layers, and human engineering activities; (2) The vulnerability assessment shows that the study area presents the distribution characteristics of "low in the north and high in the south", and the Stacking integrated model has the best prediction accuracy , which is significantly better than the single model and the traditional information model. [Conclusion] This study provides high-precision data support for landslide risk prevention and control in the southern area of Dengfeng, and demonstrates the significant advantages of ensemble learning methods in susceptibility evaluation of complex terrain areas.