Abstract: Objectives: Earthquake-induced landslides, as a highly destructive and dangerous geologic hazard, the accurate assessment of their susceptibility is crucial for post-earthquake relief, mitigation, and post-disaster reconstruction. Methods: To address the limitations of convolutional neural networks (CNNs), such as susceptibility to overfitting and uncertainty in multi-source data, a novel approach based on a convolutional fuzzy neural network (CFNN) was developed. The approach combines the efficient feature extraction capability of CNN with the strong uncertainty handling capability of fuzzy logic to achieve accurate modeling and feature optimization of landslide influencing factors. Additionally, the SHAP feature optimization strategy was introduced to quantitatively evaluate feature importance, enabling the selection and optimization of model inputs. The 2017 Jiuzhaigou Ms7.0, the 2022 Lushan Ms6.1, and the 2022 Luding Ms6.8 earthquakes were selected to form the study area, which includes a total of 5,990 landslide instances covering an area of 72.147 km2. A total of 16 landslide impact factors were selected for comprehensive analysis. The CFNN model was constructed and optimized to evaluate earthquake-induced landslide susceptibility in the study area. Results: The results indicate that the distance to rivers, peak ground acceleration (PGA), elevation, soil cover type, and distance to faults are the key factors influencing landslide development. Compared to traditional CNN model, the CFNN model demonstrates superior performance and exhibits significant overfitting resistance. Furthermore, after incorporating the SHAP-based feature optimization strategy, the performance of the CFNN model was further enhanced, achieving an area under the receiver operating characteristic curve (AUC) of 0.942, indicating excellent predictive accuracy. Conclusions: The results verify the reliability of the CFNN model in earthquake-induced landslide susceptibility evaluation, providing a new theoretical basis and technical support for the prevention and monitoring of such disasters. Moreover, these results provide a valuable reference for advancing the application of deep learning models in geohazard studies.