Effective monitoring of the slope deformation of an open-pit mine is essential for preventing catastrophic collapses. It is a challenging task to accurately predict slope deformation. To this end, this article proposed a new machine-learning method for slope deformation prediction. Ground-based interferometric radar (GB-SAR) was employed to collect the slope deformation data from an open-pit mine. Then, an ensemble learner, which aggregated a set of weaker learners, was proposed to mine the GB-SAR field data, delivering a slope deformation prediction model. The evaluation of the field data acquired from the Anjialing open-pit mine demonstrates that the proposed slope deformation model was able to precisely predict the slope deformation of the monitored mine. The prediction accuracy of the super learner was superior to those of all the independent weaker learners.

Mine disasters often happen unpredictably and it is necessary to find an effective deformation forecasting method. A model between deformation data and the factors data that affected deformation is built in this study. The factors contain hydro-geological factors and meteorological factors. Their relationship presents a complex nonlinear relationship which cannot be solved by ordinary methods such as multiple linear regression. With the development of artificial intelligence algorithm, Artificial Neural Network, Support Vector Machine, and Extreme Learning Machine come to the fore. Support Vector Machine could establish a deformation prediction model perfectly in the condition that there is less input data and output data. The deformation forecast model that uses quantum-behaved particle swarm optimization algorithm is selected to optimize the Support Vector Machine. The optimum configuration of Support Vector Machine model needs to be determined by two parameters, that is, normalized mean square error and correlation coefficient (R). Quantum-behaved particle swarm optimization could determine the optimal parameter values by minimizing normalized mean square error. It investigates the application effect of the proposed quantum-behaved particle swarm optimization–Support Vector Machine model by comparing their performances of popular forecasting models, such as Support Vector Machine, GA-Support Vector Machine, and particle swarm optimization–Support Vector Machine models. The results show that the proposed model has better performances in mine slope surface deformation and is superior to its rivals.

At present, due to the complex and changeable geological conditions, the precise deformation prediction technology of high and steep slope could not achieve an accurate prediction. In particular, the single forecasting model has some problems such as poor stability, low precision, and data fluctuation. In practice, excavating the complex nonlinear relationship between open-pit slope surface deformation monitoring data and various influencing factors and improving the accuracy of the deformation prediction of high and steep slopes is the key to safe open-pit mine production. It proposed to introduce the position factor and the velocity factor into a twin support vector machine (TWSVM). The adaptive subgroup optimisation (APSO) algorithm is selected for parameter optimisation. Through the comparative analysis of TWSVM, genetic algorithm-TWSVM (GA-TWSVM), and the proposed APSO⁃TWSVM, the experimental data show that the mean absolute error (MAE) values of the three models are 13.29 %，8.17 %, and 1.27 %, the RMSE - 47.83 %，6.52 %, and 3.02 %, respectively; the prediction time for APSO⁃TWSVM is improved by 62.5 % compared to GA-TWSVM.

High-intensity ground operations in mining areas easily disrupt ecological balance and threaten ground safety, necessitating precise measurement and monitoring of surface deformation. Deep learning-based crack segmentation enables accurate localization and quantitative measurement of crack dimensions. Existing models mostly adopt large-scale improvement mechanisms or cumbersome modules to boost accuracy, but these introduce excessive parameters and computational costs. Conversely, lightweight models compromise segmentation precision, particularly for fine-scale crack measurement. Thus, this paper proposes the DP-MCUNet++ model for automatic and accurate extraction of fine ground cracks from unmanned aerial vehicle (UAV) images, achieving an optimal balance between accuracy and efficiency. Building upon UNet++, it implements three key innovations: (1) removes the deep supervision pruning mechanism, reducing parameters by 15% while maintaining accuracy; (2) replaces standard convolutional modules with a dual-path encoder that separately captures semantic context and spatial details through parallel processing, enabling lightweight operation (10.25M parameters) with diverse feature extraction; (3) introduces Convolutional Block Attention Module (CBAM) to integrate pixel spatial and feature channel dependencies for suppressing background interference, and designs Multi-scale Attention Aggregation Mechanism (MSAA). for adaptive multi-scale feature aggregation to handle crack scale variations. The model is validated on three diverse datasets including our self-collected Huipodi mining area dataset, CrackTree200, and Crack-Flickr Dataset (CFD), demonstrating strong generalization capability across different crack types and environmental conditions. Experiments demonstrate that the proposed DP-MCUNet++ achieves 81.05% Recall, 83.17% F1-score, and 81.02% mIoU on the Huipodi dataset, with an inference speed of 5.98 FPS. It outperforms traditional image processing methods and state-of-the-art deep learning networks while maintaining computational efficiency suitable for practical deployment. Cross-validation on two public benchmarks, CrackTree200 and CFD, confirms robust generalization capability. The method provides quantitative crack measurement accuracy of ±2.58 cm for width and ±3.87 cm for length at a ground sampling distance of 1.29 cm, meeting measurement standards for ground safety assessment and ecological protection.

Automatic detection of road cracks is essential for the long-term safety maintenance of roads, bridges, and other infrastructure. Although existing deep learning-based crack segmentation methods have improved detection accuracy, challenges remain in terms of high computational complexity and inadequate capture of fine cracks and edge details. To address these issues, this study proposes an enhanced UNet-based architecture, termed DynaEdge-Net. In the encoder and decoder stages, a Residual Detail Enhancement Block (RDEB) and a Cascaded Group Attention (CGA) module are incorporated to strengthen edge feature representation and focus on critical regions, respectively. In the skip connections, a Group-wise Dynamic Gating (GDG) module is introduced to adaptively suppress background noise and optimize feature transmission. During decoding, a Dynamic Upsampling (DySample) strategy replaces conventional interpolation, enabling high-fidelity reconstruction of crack structures. Experimental results show that DynaEdge-Net achieves IoU, F1-score, boundary F1-score, and recall rates of 82.34%, 90.83%, 83.27%, and 90.12%, respectively, outperforming several state-of-the-art road segmentation algorithms. The proposed method not only improves the continuity and accuracy of crack extraction but also demonstrates strong robustness and generalization capability, providing a reliable solution for intelligent inspection and maintenance of transportation infrastructure.

This study employed Moderate-Resolution Imaging Spectroradiometer (MODIS) aerosol optical depth data meteorological data, Digital Elevation Model (DEM), Normalized Difference Vegetation Index (NDVI), and ground monitoring data for particulate matter (PM2.5) to construct a model for estimating the PM2.5 concentration in Yangquan City, Shanxi Province, from 2015 to 2024. The spatial and temporal changes in the PM2.5 concentration were analyzed. The results revealed the following: (1) The random forest model was more accurate than the multiple linear regression model. The spring model R² increased by 38.7%, and the Root Mean Square Error (RMSE) decreased by 92.6%. The summer model R² increased by 65.1%, and the RMSE decreased by 92.5%. The autumn model R² increased by 2.7%, and the RMSE decreased by 83.4%. The winter model R² increased by 25.4%, and the RMSE decreased by 95.5%. (2) The PM2.5 concentration in Yangquan City showed an upward trend from 2015 to 2017, and then a downward trend from 2018 to 2024, with an average decrease of 18.3 μg/m³. The highest concentration of PM2.5 was 55–85 μg/m³ in winter, and the lowest concentration of PM2.5 was 25–40 μg/m³ in summer. In terms of spatial distribution, the PM2.5 concentration in Yangquan City exhibits a pattern of being lower in the northwest and higher in the southeast. The high values are primarily concentrated in the central urban areas and major industrial zones in the southeast.