A hybrid neural network-based model for landslide susceptibility mapping_data

Landslides represent one of the most destructive geological hazards worldwide, where susceptibility assessment serves as a critical component in regional landslide risk management. To address the limitations of conventional methods in spatial representation, class imbalance handling, and temporal feature extraction, this study proposes a Buffer-SMOTE-Transformer comprehensive optimization framework. The framework integrates geospatial buffer sampling techniques to refine negative sample selection, employs SMOTE algorithm to effectively resolve class imbalance issues, and incorporates a weighted hybrid Transformer network to enhance modeling capability for complex geographical features. An empirical analysis conducted in China's Guangdong Province demonstrates that the BST model reveals the varying impacts of sample selection, dataset construction, and model performance on assessment outcomes. The framework achieves significant superiority over conventional machine learning methods (Random Forest, LGB) in key metrics, with AUC reaching 0.964 and Recall attaining 0.953. These findings not only elucidate the cascading amplification effects of comprehensive optimization in susceptibility modeling but also establish a novel technical pathway for large-regional-scale geological hazard risk assessment.