Complex cross-regional landslide susceptibility mapping by multi-source domain transfer learning

• A novel transfer learning landslide susceptibility mapping method is proposed. • The first time multi-source domain TL strategy for complex “no-sample” region. • The method is effective in removing the landslide feature shift between domains. • Independent landslide classifiers can interpret critical disaster samples. • LSM results integrate landslide transfer knowledge from multiple source domains. Landslide susceptibility evaluation plays an important role in disaster prevention and reduction. Feature-based transfer learning (TL) is an effective method for solving landslide susceptibility mapping (LSM) in target regions with no available samples. However, as the study area expands, the distribution of landslide types and triggering mechanisms becomes more diverse, leading to performance degradation in models relying on landslide evaluation knowledge from a single source domain due to domain feature shift. To address this, this study proposes a Multi-source Domain Adaptation Convolutional Neural Network (MDACNN), which combines the landslide prediction knowledge learned from two source domains to perform cross-regional LSM in complex large-scale areas. The method is validated through case studies in three regions located in southeastern coastal China and compared with single-source domain TL models (TCA-based models). The results demonstrate that MDACNN effectively integrates transfer knowledge from multiple source domains to learn diverse landslide-triggering mechanisms, thereby significantly reducing prediction bias inherent to single-source domain TL models, achieving an average improvement of 16.58% across all metrics. Moreover, the landslide susceptibility maps generated by MDACNN accurately quantify the spatial distribution of landslide risks in the target area, providing a powerful scientific and technological tool for landslide disaster management and prevention.