Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly and accurately is the basis of landslide disaster prevention. Fengjie County, Chongqing, China, is a typical landslide-prone area in the Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) and Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Additive Boosting (AdaBoost). We construct four new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, and SHAP-OPT-AdaBoost) and apply the four new models to landslide extraction for the first time. Firstly, high-resolution remote sensing images were preprocessed, landslide and non-landslide samples were constructed, and an initial feature set with 48 features was built. Secondly, SHAP was used to select features with significant contributions, and the important features were selected. Finally, Optuna, the Bayesian optimization technique, was utilized to automatically select the basic models’ best hyperparameters. The experimental results show that the accuracy (ACC) of these four SHAP-OPT models was above 92% and the training time was less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved the highest accuracy (96.26%). Landslide distribution information in Fengjie County from 2013 to 2020 can be extracted by SHAP-OPT-XGBoost accurately and quickly.

Semantic segmentation plays a crucial role in interpreting remote sensing images, especially in high-resolution scenarios where finer object details, complex spatial information and texture structures exist. To address the challenge of better extracting semantic information and ad-dressing class imbalance in multiclass segmentation, we propose utilizing diffusion models for remote sensing image semantic segmentation, along with a lightweight classification module based on a spatial-channel attention mechanism. Our approach incorporates unsupervised pretrained components with a classification module to accelerate model convergence. The diffusion model component, built on the UNet architecture, effectively captures multiscale features with rich contextual and edge information from images. The lightweight classification module, which leverages spatial-channel attention, focuses more efficiently on spatial-channel regions with significant feature information. We evaluated our approach using three publicly available datasets: Postdam, GID, and Five Billion Pixels. In the test of three datasets, our method achieved the best results. On the GID dataset, the overall accuracy was 96.99%, the mean IoU was 92.17%, and the mean F1 score was 95.83%. In the training phase, our model achieved good performance after only 30 training cycles. Compared with other models, our method reduces the number of parameters, improves the training speed, and has obvious performance advantages.

Extreme loadings, a hostile environment and dangerous operation lead to the unsafe state of bridges under construction, especially large-span bridges. Global Navigation Satellite Systems (GNSS) tend to be the best choice for real-time deformation monitoring due to the significant advantage of automation, continuation, all-weather operation and high precision. Unfortunately, the traditional geodetic GNSS instrument with its high price and large volume is limited in its applications. Hence, we design and develop low-cost GNSS equipment by simplifying the monitoring module. The performance of the proposed solution is evaluated through an experimental dynamic scenario, proving its ability to track abrupt deformation down to 3–5 mm. We take Chongqing Guojiatuo Suspension Bridge in China as a case study. We build a real-time low-cost GNSS monitoring cloud platform. The low-cost bridge GNSS monitoring stations are located at the top of the south and north towers, midspan upstream and downstream respectively and the reference station is located in the stable zone 400 m away from the bridge management buildings. We conducted a detailed experimental assessment of low-cost GNSS on 5 April and a real-time deformation detection experiment of the towers and main cables during the dynamic cable saddle pushing process on 26 February 2022. In the static experiment, the standard deviation of the residual using the multi-GNSS solution is 2 mm in the horizontal direction and 5 mm in the vertical direction. The multi-GNSS solution significantly outperforms the BDS/GPS single system. The dynamic experiment shows that, compared with the movement measured by the robotic total station, the horizontal error of the south tower and north tower measured by low-cost GNSS is below 0.005 m and 0.008 m respectively. This study highlights the potential of low-cost GNSS solutions for Structural Health Monitoring (SHM) applications.

Insulators are key components to ensure the normal operation of power facilities in transmission corridors. Existing insulator identification methods mainly use image data and lack the acquisition of three-dimensional information. This paper proposes an efficient insulator extraction method based on UAV (unmanned aerial vehicle) LiDAR (light detection and ranging) point cloud, using five histogram features: horizontal density (HD), horizontal void (HV), horizontal width (HW), vertical width (VW) and vertical void (VV). Firstly, a voxel-based method is employed to roughly extract power lines and pylons from the original point cloud. Secondly, the VV histogram is used to categorize the pylons into suspension and tension types, and the HD histogram is used to locate the tower crossarm and further refine the roughly extracted powerlines. Then, for the suspension tower, insulators are segmented based on the HV histogram and HD difference histogram. For the tension tower, the HW histogram is used to recognize the jumper conductor (JC) and transmission conductor (TC) from the power line. The HW histogram and VW histogram are used to extract the tension insulator in the TC and suspension insulator in the JC, respectively. Finally, considering the problem of setting a suitable grid width when constructing the feature histogram, an adaptive method of multi-scale histograms is proposed to refine the extraction result. Two 220 kV long transmission lines are used for the validation, and the overall object-based accuracy for suspension and tension towers are 100% and 97.3%, respectively. Compared with the point feature-based method, the mean F1 score of the proposed method improved by 0.3, and the runtime for each tower is within 2 s.

Urban vegetation plays a crucial role in the urban ecological system. Efficient and accurate extraction of urban vegetation information has been a pressing task. Although the development of deep learning brings great advantages for vegetation extraction, there are still problems, such as ultra-fine vegetation omissions, heavy computational burden, and unstable model performance. Therefore, a Separable Dense U-Net (SD-UNet) was proposed by introducing dense connections, separable convolutions, batch normalization layers, and Tanh activation function into U-Net. Furthermore, the Fake sample set (NIR-RG), NDVI sample set (NDVI-RG), and True sample set (RGB) were established to train SD-UNet. The obtained models were validated and applied to four scenes (high-density buildings area, cloud and misty conditions area, park, and suburb) and two administrative divisions. The experimental results show that the Fake sample set can effectively improve the model’s vegetation extraction accuracy. The SD-UNet achieves the highest accuracy compared to other methods (U-Net, SegNet, NDVI, RF) on the Fake sample set, whose ACC, IOU, and Recall reached 0.9581, 0.8977, and 0.9577, respectively. It can be concluded that the SD-UNet trained on the Fake sample set not only is beneficial for vegetation extraction but also has better generalization ability and transferability.

Real-time monitoring of urban building development provides a basis for urban planning and management. Remote sensing change detection is a key technology for achieving this goal. Intelligent change detection based on deep learning of remote sensing images is a current focus of research. However, most methods only use unimodal remote sensing data and ignore vertical features, leading to incomplete characterization, poor detection of small targets, and false detections and omissions. To solve these problems, we propose a multi-path self-attentive hybrid coding network model (MAHNet) that fuses high-resolution remote sensing images and digital surface models (DSMs) for 3D change detection of urban buildings. We use stereo images from the Gaofen-7 (GF-7) stereo mapping satellite as the data source. In the encoding stage, we propose a multi-path hybrid encoder, which is a structure that can efficiently perform multi-dimensional feature mining of multimodal data. In the deep feature fusion link, a dual self-attentive fusion structure is designed that can improve the deep feature fusion and characterization of multimodal data. In the decoding stage, a dense skip-connection decoder is designed that can fuse multi-scale features flexibly and reduce spatial information losses in small-change regions in the down-sampling process, while enhancing feature utilization and propagation efficiency. Experimental results show that MAHNet achieves accurate pixel-level change detection in complex urban scenes with an overall accuracy of 97.44% and F1-score of 92.59%, thereby outperforming other methods of change detection.