Landslide event warning in mining areas is essential for geohazard risk mitigation and infrastructure safety. With the increasing use of Global Navigation Satellite System (GNSS) monitoring networks, warning decisions are often derived from abnormal deformation responses in continuous displacement records. However, deriving stable and transferable warning decisions from GNSS networks is challenged by spatially coupled station responses, time-varying displacement patterns, and incomplete or disturbed observations. To address these issues, this study proposes a graph-augmented gradient boosting decision tree framework, termed GA-GBDT (Graph-Augmented Gradient Boosting Decision Trees), for multi-station landslide event warning in mining areas. The framework first constructs a weighted station graph to encode spatial dependence across stations. Based on this graph, a Gated Recurrent Unit (GRU) and a Graph Convolutional Network (GCN) are integrated to learn spatio-temporal embeddings, which are then fused with station-wise features and fed into XGBoost (eXtreme Gradient Boosting) for warning decision-making. Experiments on a 90-station GNSS network show that GA-GBDT outperforms representative rule-based, machine-learning, and deep-learning baselines, achieving more robust warning performance with improved generalization and false-alarm control. These results indicate that GA-GBDT improves warning robustness, decision stability, and cross-zone generalization for GNSS-based landslide warning in mining areas, with potential transferability to other slope warning scenarios.

Recent advances in measurement technologies have significantly improved the accuracy of multi-scale 3D reconstruction, yet the resulting large-scale data with inherent redundancy pose challenges for storage and real-time rendering. This paper proposes a systematic framework for efficient lightweight processing of 3D real-scene mesh model, integrating planar feature extraction, point cloud classification, and semantics-driven simplification. The key scientific contributions include: (1) A preprocessing process for the reality 3D model is added for the plane segmentation algorithm; (2) A training-free point cloud classification method employing 9 complementary geometric-semantic features and probabilistic smoothing to achieve computationally efficient classification without the need for deep learning or annotated data; and (3) An innovative semantic-driven simplification strategy that dynamically adjusts processing priorities based on feature importance. Experimental results demonstrate the framework's effectiveness in preserving critical architectural features (e.g., façades and roofs) while aggressively compressing less significant elements (e.g., terrain and clutter), achieving balanced data reduction and information retention. At equivalent simplification ratios, our algorithm achieves a 23% improvement in model accuracy compared to the baseline method, with a 31% accuracy enhancement specifically for critical geometric features. When maintaining equivalent accuracy levels, the proposed method reduces face count by 23% relative to the baseline approach. The proposed methods advance 3D urban modeling by addressing both technical and practical challenges in large-scale scene processing.

With the advancement of urbanization, building footprint data plays an important role in urban planning, 3D Real Scene and smart cities. Traditional manual contouring methods are time-consuming and laborious, while deep learning-based building extraction methods often require a large amount of labeled data and have limited generalization ability. In this paper, a zero-shot framework based on Segment Anything Model (SAM) is proposed for extracting and regularing building footprints from 3D mesh data. The method mainly consists of three steps: 1) Coarse Prompt Generation, irrelevant element’s masks such as ground and vegetation are eliminated by semi-global filtering and traditional classification method, and rough building mask is obtained as a boundary box prompt. 2) Fine mask generation: Using SAM's mask prompt capability, combined with logits map and grid elevation information with adaptive threshold to generate the fine mask prompt. Combine it with the updated bounding box to form hybrid prompt, and input SAM to generate a refined building mask. 3) Footprint regularization: Kinetic Partition, Markov random field, and Region Growth Algorithm are used to extract regularized building contours. Structural line segments from LSD guide the Kinetic Partitioning of the building. Markov random field matches building labels, while a region growth-based boundary reassignment refines the contours. The final regularized contour integrates the partitioned building zones. Our method achieved 78.31% AP50 on the Vaihingen dataset and obtained regular footprints that closely align with the true building contours on real Mesh data.