The accurate prediction of surface subsidence induced by coal mining is critical to safeguarding the environment and resources. However, the precision of current prediction models is often restricted by the lack of pertinent data or imprecise model parameters. To overcome these limitations, this study proposes an approach to predicting mine subsidence that leverages Interferometric Synthetic Aperture Radar (InSAR) technology and the long short-term memory network (LSTM). The proposed approach utilizes small baseline multiple-master high-coherent target (SBMHCT) interferometric synthetic aperture radar technology to monitor the mine surface and applies the long short-term memory (LSTM) algorithm to construct the prediction model. The Shigouyi coalfield in Ningxia Province, China was chosen as a study area, and time series ground subsidence data were obtained based on Sentinel-1A data from 9 March 2015 to 7 June 2016. To evaluate the proposed approach, the prediction accuracies of LSTM and Support Vector Regression (SVR) were compared. The results show that the proposed approach could accurately predict mine subsidence, with maximum absolute errors of less than 2 cm and maximum relative errors of less than 6%. The findings demonstrate that combining InSAR technology with the LSTM algorithm is an effective and robust approach for predicting mine subsidence.

Mining subsidence is time-dependent and highly nonlinear, especially in the Loess Plateau region in Northwestern China. As a consequence, and mainly in building agglomerations, the structures can be damaged severely during or after underground extraction, with risks to human life. In this paper, we propose an approach based on a combination of a differential interferometric synthetic aperture radar (DInSAR) technique and a support vector machine (SVM) regression algorithm optimized by grid search (GS-SVR) to predict mining subsidence in a timely and cost-efficient manner. We consider five Advanced Land Observing Satellite (ALOS)/Phased Array type L-band Synthetic Aperture Radar (PALSAR) images encompassing the Dafosi coal mine area in Binxian and Changwu counties, Shaanxi Province. The results show that the subsidence predicted by the proposed InSAR and GS-SVR approach is consistent with the Global Positioning System (GPS) measurements. The maximum absolute errors are less than 3.1 cm and the maximum relative errors are less than 14%. The proposed approach combining DInSAR with GS-SVR technology can predict mining subsidence on the Loess Plateau of China with a high level of accuracy. This research may also help to provide disaster warnings.

In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.

In China, the Loess Plateau’s fragile geological structure leads to complex and variable surface subsidence in old gob areas following coal mining activities. Accurately predicting this residual subsidence remains a significant scientific challenge. In this study, a method for residual subsidence prediction using an Exponential Smoothing Long Short-Term Memory (EsLSTM) model is proposed. The investigation centers on the 18,001# old goaf area of the Yangquan Coal Mine in Shanxi Province. Using Sentinel-1A imagery, continuous SAR data from 98 periods were acquired and processed via Enhanced Distributed Scatter InSAR technology. The EsLSTM model was then developed to capture the subsidence time-series characteristics of all surface scatter points and predict future ground subsidence. The analysis reveals that the EsLSTM model delivered excellent accuracy, achieving an R2 value of 0.975. It also outperformed SVR and traditional LSTM models, with a Mean Absolute Error of 2.2 mm and a Root Mean Square Error of 7.9 mm. Predicted results indicate that by October 2023, the maximum cumulative subsidence at the 18,001# working face of the Yangquan Coal Mine will reach 204 mm. The subsidence trend is expected to become more gradual and stable, suggesting a low likelihood of geological disasters in the area.

Accurate monitoring of mining-induced three-dimensional surface deformation is critical for safety and environmental protection. Conventional InSAR often loses coherence in high-deformation areas and provides only one-dimensional measurements, while the Probability Integral Model (PIM) suffers from low accuracy at subsidence edges, caused by premature numerical convergence of its error-function-based mathematical formulation—the model prediction rapidly drops to zero and fails to capture subtle real-world deformations in marginal zones. This study developed a fusion method integrating multi-source InSAR (Sentinel-1A and SAOCOM), PIM, and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Applied in the Yinying Mining Area, Shanxi Province, the approach combined ascending and descending SAR data processed via SBAS-InSAR, used CMA-ES to optimize PIM parameter inversion, and employed a zonal fusion strategy to reconstruct complete deformation fields. The method demonstrated substantial improvement in monitoring accuracy, with mean absolute errors in the vertical, north–south, and east–west directions reduced by more than 86% compared with the standalone PIM model in edge zones. The fusion approach effectively captured both large-magnitude center deformations and subtle edge displacements. Multi-source data fusion with intelligent optimization algorithms significantly enhances the accuracy of 3D deformation monitoring in mining areas, providing reliable technical support for safety management and environmental protection.

Point cloud registration under partial overlap and heavy outliers remains a significant challenge. Jointly optimizing the transformation and correspondences provides robustness to missing data and distortion, yet existing Branch-and-Bound (BnB) methods are limited by high-dimensional search spaces, loose term-wise bounds, or restrictive full-overlap assumptions. This paper presents BnB-MS, a new BnB algorithm that reformulates registration as an outlier-aware mode-seeking problem. The reformulation reduces the original non-convex objective to a tractable quadratic form whose low-rank structure enables the search to operate in a space whose dimension is independent of the number of points. It also admits a tight holistic lower bound that captures the interactions among all terms, leading to faster convergence and improved robustness under heavy outlier contamination. Experiments on 2D/3D synthetic and real datasets demonstrate the effectiveness of the proposed method under challenging registration conditions.