Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods.

On 18 May 2026, a M5.2 double earthquake struck the Taiyangzhen area of Liunan District, Liuzhou City, Guangxi, China, triggering shallow surface collapses in this karst terrain. We conducted three UAV orthophoto surveys of the meizoseismal area on 20 May, 23 May, and 24 May, and interpreted 17 collapse monitoring units from the imagery. The total collapse area increased from 75.3 m² on 20 May to 499.1 m² on 23 May, and further to 553.9 m² on 24 May. On 20 May, only 7 of 17 units exhibited collapses; by 23 May, all 17 units were affected. Among them, 7 pre-existing collapse patches expanded, and 10 new collapses emerged between 20 and 23 May. Depth measurements revealed measurable depths of 0.18–7.60 m for 7 collapses, and all 6 units with bi-temporal depth data showed continued deepening from 23 to 24 May. Ponding water was observed in up to 10 units, consistent with the 98.7 mm of rainfall recorded during 18–24 May. Multi-temporal UAV surveys reveal that post-seismic surface collapse development in karst terrain extends well beyond the mainshock, with both rapid expansion of pre-existing failures and delayed emergence of new collapses driven by the coupled effects of seismic weakening and hydrologic forcing.

The Upper Jinsha River region on the southeastern Tibetan Plateau is characterized by intense tectonic activity, extreme topographic relief, and widespread large-scale landslides, which pose significant threats to communities, transportation networks and major infrastructure. However, accurate landslide susceptibility assessment in high-relief mountainous terrain remains challenging. Conventional methods rely on point-based sampling and static environmental factors, which fail to capture the spatial heterogeneity of large landslides and adequately represent the influence of continuous surface deformation on landslide evolution, resulting in considerable uncertainty and limited predictive accuracy. To address these issues, this study established a polygon-based landslide inventory comprising 3831 landslides and developed an improved susceptibility assessment framework integrating multi-scale polygon-based sampling with InSAR-derived surface deformation constraints. By coupling the Random Forest (RF) and Optimized Frequency Ratio (OFR) models, quantitative susceptibility assessment and model validation were conducted. The results show that the integrated RF-OFR model achieved the best predictive performance, with an Area Under the Curve (AUC) of 0.906, representing improvements of 6.0%, 4.2%, and 2.7% over the conventional FR, RF-FR, and OFR models, respectively. Fluvial incision, terrain relief, and precipitation were identified as the dominant conditioning factors controlling regional landslide occurrence. High-susceptibility zones are primarily distributed along the Jinsha River and deeply incised tributary valleys, showing strong spatial agreement with active fault zones and persistent surface deformation. Compared with conventional single-scale point sampling, the proposed multi-scale polygon sampling strategy more effectively represents the spatial characteristics of large landslides in high-relief mountain regions, reduces sampling bias and incorporating InSAR-derived deformation information further enhances the identification of actively deforming slopes, demonstrating the value of integrating dynamic surface deformation with conventional environmental factors in landslide susceptibility modeling. The proposed framework provides an effective approach for regional landslide susceptibility assessment and can support hazard identification and risk-informed infrastructure and land use planning in high-relief mountainous regions.