Landslide deformation monitoring via InSAR is crucial for assessing the risk of hazards. Quick and accurate detection of active deformation zones is crucial for early warning and mitigation planning. While the application of deep learning has substantially improved the detection efficiency, several challenges still persist, such as poor multi-scale perception, blurred boundaries, and limited model generalization. This study proposes Hybrid-SegUFormer to address these limitations. The model integrates the SegFormer encoder’s efficient feature extraction with the U-Net decoder’s superior boundary restoration. It introduces a multi-scale fusion decoding mechanism to enhance context perception structurally and incorporates a self-distillation strategy to significantly improve generalization capability. Hybrid-SegUFormer achieves detection performance (98.79% accuracy, 80.05% F1-score) while demonstrating superior multi-scale adaptability (IoU degradation of only 6.99–8.83%) and strong cross-regional generalization capability. The synergistic integration of its core modules enables an optimal balance between precision and recall, making it particularly effective for complex landslide detection tasks. This study provides a new approach for intelligent interpretation of InSAR deformation in complex mountainous areas.

Rainfall-induced landslide deformation is governed by both intrinsic geological conditions and external dynamic triggers. However, many existing predictive models rely primarily on rainfall inputs, which limits their interpretability and robustness. To address these shortcomings, this study introduces a group-based data augmentation method informed by displacement curve morphology and proposes a multi-slope predictive framework that integrates static geological attributes with dynamic triggering factors. Using monitoring data from 274 sites across China, the framework was implemented with a Temporal Fusion Transformer (TFT) and benchmarked against baseline models, including SVR, XGBoost, and LSTM models. The results demonstrate that group-based augmentation enhances the stability and accuracy of predictions, while the integrated dynamic–static TFT framework delivers superior accuracy and improved interpretability. Statistical significance testing further confirms consistent performance improvements across all groups. Collectively, these findings highlight the framework’s effectiveness for short-term landslide forecasting and underscore its potential to advance early warning systems.

Remote sensing building change detection (RSBCD) is critical for land surface monitoring and understanding interactions between human activities and the ecological environment. However, existing deep learning-based RSBCD methods often result in mis-detected pixels concentrated around object boundaries, mainly due to ambiguous object shapes and complex spatial distributions. To address this problem, we propose a new Multiscale Edge-Aware change detection Network (MEANet) that accurately locates edge pixels of changed objects and enhances the separability between changed and unchanged pixels. Specifically, a high-resolution feature fusion network is adopted to preserve spatial details while integrating deep semantic information, and a multi-scale supervised contrastive loss (MSCL) is designed to jointly optimize pixel-level discrimination and embedding space separability. To further improve the handling of difficult samples, hard negative sampling is adopted in the contrastive learning process. We conduct comparative experiments on three benchmark datasets. Both Visual and quantitative results demonstrate that our new MEANet significantly reduces misclassified pixels at object boundaries and achieve superior detection accuracy compared to existing methods. Especially on the GZ-CD dataset, MEANet improves F1-Score and mIoU by more than 2% compared with ChangeFormer, demonstrating strong robustness in complex scenarios. It is worth noting that the performance of MEANet may still be affected by extremely complex edge textures or highly blurred boundaries. Future work will focus on further improving robustness under such challenges and extending the method to broader RSBCD scenarios.