Accurate prediction of short-term rockburst has a significant role in improving the safety of workers in mining and geotechnical projects. The rockburst occurrence is nonlinearly correlated with its influencing factors that guarantee imprecise predicting results by employing the traditional methods. In this study, three approaches including including t-distributed stochastic neighbor embedding (t-SNE), K-means clustering, and extreme gradient boosting (XGBoost) were employed to predict the short-term rockburst risk. A total of 93 rockburst patterns with six influential features from micro seismic monitoring events of the Jinping-II hydropower project in China were used to create the database. The original data were randomly split into training and testing sets with a 70/30 splitting ratio. The prediction practice was followed in three steps. Firstly, a state-of-the-art data reduction mechanism t-SNE was employed to reduce the exaggeration of the rockburst database. Secondly, an unsupervised machine learning, i.e., K-means clustering, was adopted to categorize the t-SNE dataset into various clusters. Thirdly, a supervised gradient boosting machine learning method i.e., XGBoost was utilized to predict various levels of short-term rockburst database. The classification accuracy of XGBoost was checked using several performance indices. The results of the proposed model serve as a great benchmark for future short-term rockburst levels prediction with high accuracy.

Accurate and quantitative investigation of the physical structure and fractal geometry of coal has important theoretical and practical significance for coal bed methane (CBM) development and the prevention of dynamic disasters such as coal and gas outbursts. This study investigates the pore structure and fractal characteristics of soft and hard coals using nitrogen and carbon dioxide (N₂/CO₂) adsorption. Coal samples from Pingdingshan Mine in Henan province of China were collected and pulverized to the required size (0.20–0.25 mm). N₂/CO₂ adsorption tests were performed to evaluate the specific surface area (SSA), pore size distribution (PSD), and pore volume (PV) using Braunuer-Emmett-Teller (BET), Barrett-Joyner-Halenda (BJH), and Density Functional Theory (DFT). The pore structure was characterized based on the theory of fractal dimensions. The results unveiled that the strength of coal has a significant influence on pore structure and fractal dimensions. There are significant differences in SSA and PV between both coals. The BJH-PV and BET-SSA obtained by N₂-adsorption for soft coal are 0.029–0.032 cm³/g and 3.523–4.783 m²/g. While the values of PV and SSA obtained by CO₂-adsorption are 0.037–0.039 cm³/g and 106.016–111.870 m²/g. Soft coal shows greater SSA and PV than hard coal, which is consistent with the adsorption capacity ( $${V}_{\mathrm{L}}$$V L ). The fractal dimensions of soft and hard coal are respectively different. The Ding coal exhibits larger D₁ and smaller D₂, and the reverse for the Wu coal seam is observed. The greater the value of D₁ (complexity of pore surface) of soft coal is, the larger the pore surface roughness and gas adsorption capacity is. The results enable us to conclude that the characterization of pores and fractal dimensions of soft and hard coals is different, tending to different adsorption/desorption characteristics. In this regard, the results provide a reference for formulating corresponding coal and gas outburst prevention and control measures.

Uniaxial compressive strength (UCS) and the static Young’s modulus (E_s) are fundamental parameters for the effective design of engineering structures in a rock mass environment. Determining these two parameters in the laboratory is time-consuming and costly, and the results may be inappropriate if the testing process is not properly executed. Therefore, most researchers prefer alternative methods to estimate these two parameters. This work evaluates the thermal effect on the physical, chemical, and mechanical properties of marble rock, and proposes a prediction model for UCS and E_S using multi-linear regression (MLR), artificial neural networks (ANNs), random forest (RF), and k-nearest neighbor. The temperature (T), P-wave velocity (P_V), porosity (η), density (ρ), and dynamic Young’s modulus (E_d) were taken as input variables for the development of predictive models based on MLR, ANN, RF, and KNN. Moreover, the performance of the developed models was evaluated using the coefficient of determination (R²) and mean square error (MSE). The thermal effect results unveiled that, with increasing temperature, the UCS, E_S, P_V, and density decrease while the porosity increases. Furthermore, ES and UCS prediction models have an R² of 0.81 and 0.90 for MLR, respectively, and 0.85 and 0.95 for ANNs, respectively, while KNN and RF have given the R² value of 0.94 and 0.97 for both E_S and UCS. It is observed from the statistical analysis that P-waves and temperature show a strong correlation under the thermal effect in the prediction model of UCS and E_S. Based on predictive performance, the RF model is proposed as the best model for predicting UCS and E_S under thermal conditions.

The safe and sustainable design of rock slopes, open-pit mines, tunnels, foundations, and underground excavations requires appropriate and reliable estimation of rock strength and deformation characteristics. Cohesion (𝑐) and angle of internal friction (𝜑) are the two key parameters widely used to characterize the shear strength of materials. Thus, the prediction of these parameters is essential to evaluate the deformation and stability of any rock formation. In this study, four advanced machine learning (ML)-based intelligent prediction models, namely Lasso regression (LR), ridge regression (RR), decision tree (DT), and support vector machine (SVM), were developed to predict 𝑐 in (MPa) and 𝜑 in (°), with P-wave velocity in (m/s), density in (gm/cc), UCS in (MPa), and tensile strength in (MPa) as input parameters. The actual dataset having 199 data points with no missing data was allocated identically for each model with 70% for training and 30% for testing purposes. To enhance the performance of the developed models, an iterative 5-fold cross-validation method was used. The coefficient of determination (R²), mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and a10-index were used as performance metrics to evaluate the optimal prediction model. The results revealed the SVM to be a more efficient model in predicting 𝑐 (R² = 0.977) and 𝜑 (R² = 0.916) than LR (𝑐: R² = 0.928 and 𝜑: R² = 0.606), RR (𝑐: R² = 0.961 and 𝜑: R² = 0.822), and DT (𝑐: R² = 0.934 and 𝜑: R² = 0.607) on the testing data. Furthermore, to check the level of accuracy of the SVM model, a sensitivity analysis was performed on the testing data. The results showed that UCS and tensile strength were the most influential parameters in predicting 𝑐 and 𝜑. The findings of this study contribute to long-term stability and deformation evaluation of rock masses in surface and subsurface rock excavations.

Snow avalanches are a type of serious natural disaster that commonly occur in snow-covered mountains with steep terrain characteristics. Susceptibility analysis of avalanches is a pressing issue today and helps decision makers to implement appropriate avalanche risk reduction strategies. Avalanche susceptibility maps provide a preliminary method for evaluating places that are likely to be vulnerable to avalanches to stop or reduce the risks of such disasters. The current study aims to identify areas that are vulnerable to avalanches (ranging from extremely high and low danger) by considering geo-morphological and geological variables and employing an Analytical Hierarchy Approach (AHP) in the GIS platform to identify potential snow avalanche zones in the Karakoram region in Northern Pakistan. The Advanced Space-borne Thermal Emission and Reflection Radiometer (ASTER) Global Digital Elevation Model (GDEM) was used to extract the elevation, slope, aspect, terrain roughness, and curvature of the study area. This study includes the risk identification variable of land cover (LC), which was obtained from the Landsat 8 Operational Land Imager (OLI) satellite. The obtained result showed that the approach established in this study provided a quick and reliable tool to map avalanches in the study area, and it might also work with other glacier sites in other parts of the world for snow avalanche susceptibility and risk assessments.