Landslides are most severe in the mountainous regions of southwestern China. While landslide identification provides a foundation for disaster prevention operations, methods for utilizing multi-source data and deep learning techniques to improve the efficiency and accuracy of landslide identification in complex environments are still a focus of research and a difficult issue in landslide research. In this study, we address the above problems and construct a landslide identification model based on the shifted window (Swin) transformer. We chose Ya’an, which has a complex terrain and experiences frequent landslides, as the study area. Our model, which fuses features from different remote sensing data sources and introduces a loss function that better learns the boundary information of the target, is compared with the pyramid scene parsing network (PSPNet), the unified perception parsing network (UPerNet), and DeepLab_V3+ models in order to explore the learning potential of the model and test the models’ resilience in an open-source landslide database. The results show that in the Ya’an landslide database, compared with the above benchmark networks (UPerNet, PSPNet, and DeepLab_v3+), the Swin Transformer-based optimization model improves overall accuracies by 1.7%, 2.1%, and 1.5%, respectively; the F1_score is improved by 14.5%, 16.2%, and 12.4%; and the intersection over union (IoU) is improved by 16.9%, 18.5%, and 14.6%, respectively. The performance of the optimized model is excellent.

Quantification of shading effects from complex terrain on solar radiation is essential to obtain precise data on incident solar radiation in mountainous areas. In this study, a machine learning (ML) approach is proposed to rapidly estimate the shading effects of complex terrain on solar radiation. Based on two different ML algorithms, namely, Ordinary Least Squares (OLS) and Gradient Boosting Decision Tree (GBDT), this approach uses terrain-related factors as input variables to model and analyze direct and diffuse solar radiation shading rates. In a case study of western Sichuan, the annual direct and diffuse radiation shading rates were most correlated with the average terrain shading angle within the solar azimuth range, with Pearson correlation coefficients of 0.901 and 0.97. The GBDT-based models achieved higher accuracy in predicting direct and diffuse radiation shading rates, with R² values of 0.982 and 0.989, respectively, surpassing the OLS-based models by 0.081 and 0.023. In comparisons between ML models and classic curve-fitting models, the GBDT-based models consistently performed better in predicting both the direct radiation shading rate and the diffuse radiation shading rate, with a standard deviation of residuals of 0.330% and 0.336%. The OLS-based models also showed better performance compared to the curve-fitting models.

Considering the great time and labor consumption involved in conventional hazard assessment methods in compiling landslide inventory, the construction of a transferable landslide susceptibility prediction model is crucial. This study employs UAV images as data sources to interpret the typical alpine valley area of Beichuan County. Eight environmental factors including a digital elevation model (DEM) are extracted to establish a pixel-wise dataset, along with interpreted landslide data. Two landslide susceptibility models were built, each with a deep neural network (DNN) and a support vector machine (SVM) as the learner, and the DNN model was determined to have the best pre-training performance (accuracy = 88.6%, precision = 91.3%, recall = 94.8%, specificity = 87.8%, F1-score = 93.0%, and area under curve = 0.943), with higher parameters in comparison to the SVM model (accuracy = 77.1%, precision = 80.9%, recall = 87.8%, specificity = 73.9%, F1-score = 84.2%, and area under curve = 0.878). The susceptibility model of Beichuan County is then transferred to Mao County (which has no available dataset) to realize cross-regional landslide susceptibility prediction. The results suggest that the model predictions accomplish susceptibility zoning principles and that the DNN model can more precisely distinguish between high and very-high susceptibility areas in relation to the SVM model.

Landslides are characterized by their suddenness and destructive power, making rapid and accurate identification crucial for emergency rescue and disaster assessment in affected areas. To address the challenges of limited landslide samples and data complexity, a landslide identification sample library was constructed using high-resolution remote sensing imagery combined with field validation. An innovative Dual-Coded Segmentation Network (DS Net), which realizes dynamic alignment and deep fusion of local details and global context, image features and domain knowledge through the multi-attention mechanism of Prior Knowledge Integration (PKI) module and Cross-Feature Aggregation (CFA) module, significantly improves the landslide detection accuracy and reliability. To objectively evaluate the performance of the DS Net model, four efficient semantic segmentation models—SegFormer, SegNeXt, FeedFormer, and U-MixFormer—were selected for comparison. The results demonstrate that DS Net achieves superior performance (overall accuracy = 0.926, precision = 0.884, recall = 0.879, and F1-score = 0.882), with metrics that are 3.5–7.1% higher than the other models. These findings confirm that DS Net effectively improves the accuracy and efficiency of landslide identification, providing a critical scientific basis for landslide prevention and mitigation.

Currently, the application of remote sensing technology in landslide identification and investigation is an important research direction in the field of landslides. To address the errors arising from the inaccurate extraction of texture and location information in landslide intelligent recognition, we developed a new network, the dual path attention network (DPANet), and performed experiments in a typical alpine canyon area (Wenchuan County). The results show that the new network recognizes landslide areas with an overall accuracy (OA) and pixel accuracy (PA) of 0.93 and 0.87, respectively, constituting an overall improvement of 4% and 18% compared to the base pyramid scene parsing network (PSPNet). We applied our knowledge of the landslide image features to other areas in the upper reaches of the Minjiang River to enrich the landslide database for this region. Our evaluation of the results shows that the proposed network framework has good robustness and can accurately identify some complex landslides, providing an excellent contribution to the intelligent recognition of landslides.

Landslide susceptibility prediction usually involves the comprehensive analysis of terrain and other factors that may be distributed with spatial patterns. Without considering the spatial correlation and mutual influence between pixels, conventional prediction methods often focus only on information from individual pixels. To address this issue, the present study proposes a new strategy for neighboring pixel collaboration based on the Unified Perceptual Parsing Network (UPerNet), the Vision Transformer (ViT), and Vision Graph Neural Networks (ViG). This strategy efficiently utilizes the strengths of deep learning in feature extraction, sequence modeling, and graph data processing. By considering the information from neighboring pixels, this strategy can more accurately identify susceptible areas and reduce misidentification and omissions. The experimental results suggest that the proposed strategy can predict landslide susceptibility zoning more accurately. These predictions can identify flat areas such as rivers and distinguish between areas with high and very high landslide susceptibility. Such refined zoning outcomes are significant for landslide prevention and mitigation and can help decision-makers formulate targeted response measures.