The optimization of blasting operations greatly benefits from the prediction of rock fragmentation. The main factors that affect fragmentation are rock mass characteristics, blast geometry, and explosive properties. This paper is a step towards the implementation of machine learning and deep learning algorithms for predicting the extent of fragmentation (in percentage) in open pit mining. While various parameters can affect rock fragmentation, this study considers ten among them (i.e., spacing, drill hole diameter, burden, average bench height, powder factor, number of holes, charge per delay, uniaxial compressive strength, specific drilling, and stemming) to train and test the models. However, due to a weak correlation with rock fragmentation, drill diameter, average bench height, compressive strength, stemming, and charge per delay are eliminated to reduce model complexity. A total of 219 data sets having five input features including the number of holes, spacing, burden, specific drilling, and powder factor are used to develop the models. Machine learning models (random forest regression, support vector regression, and XG boost), as well as a deep learning model (neural network regression), are applied to develop a practical way that can optimize the prediction of fragmentation. This study employs performance measures such as R-squared, RMSE, MSE, MAPE, and MAE. The optimization of the model revealed promising results, indicating that the architecture 5-64-32-16-1 exhibits strong performance. Specifically, the model achieved mean squared error (MSE) values of 41.32 and 28.59 on the training and test datasets, respectively. The R² value for both training and test is 0.83. RFR is also performing well compared to SVR and XG boost with MSE values of 12.37 and 9.89 on training and testing data, respectively.in both sets, the R² value is 94%. Based on permutation importance and shapely plot values, it is observed that the powder factor has the highest impact, while the burden has the lowest impact on fragmentation.

Mineral grade estimation is a vital phase in mine planning and design, as well as in the mining project’s economic assessment. In mining, commonly accepted methods of ore grade estimation include geometrical approaches and geostatistical techniques such as kriging, which effectively capture the spatial grade variation within a deposit. The application of machine-learning (ML) techniques has been explored in the estimation of mineral resources, where complex correlations need to be captured. In this paper, the authors developed four machine-learning regression models, i.e., support vector regression (SVR), random forest regression (RFR), k-nearest neighbour (KNN) regression, and extreme gradient boost (XGBoost) regression, using a geological database to predict the grade in an Indian iron ore deposit. When compared with ordinary kriging (R² = 0.74; RMSE = 2.09), the RFR (R² = 0.74; RMSE = 2.06), XGBoost (R² = 0.73; RMSE = 2.12), and KNN (R² = 0.73; RMSE = 2.11) regression models produced similar results. The block model predictions generated using the RFR, XGBoost, and KNN models show comparable accuracy and spatial trends to those of ordinary kriging, whereas SVR was identified as less effective. When integrated with geological methods, these models demonstrate significant potential for enhancing and optimizing mine planning and design processes in similar iron ore deposits.

Maximizing the use of explosives is crucial for optimizing blasting operations, significantly influencing productivity and cost-effectiveness in mining activities. This work explores the incorporation of machine learning methods to predict powder factor, a crucial measure for assessing the effectiveness of explosive deployment, using important rock characteristics. The goal is to enhance the accuracy of powder factor prediction by employing machine learning methods, namely decision tree models and artificial neural networks. The analysis finds key rock factors that have a substantial impact on the powder factor, hence enabling more accurate planning and execution of blasting operations. The analysis uses data from 180 blast rounds carried out at a dolomite mine in south-south Nigeria. It incorporates measures such as root mean square error (RSME), mean absolute error (MAE), R-squared (R²), and variance accounted for (VAF) to determine the best models for predicting powder factor. The results indicate that the decision tree model (MD4) outperforms alternative approaches, such as artificial neural networks and Gaussian Process Regression (GPR). In addition, the research presents an efficient artificial neural network equation (MD2) for estimating the values of optimum powder factor, demonstrating outstanding blasting fragmentation. In conclusion, this research provides significant information for improving the accuracy of powder factor prediction, which is especially advantageous for small-scale blasting operations.

Arsenic contamination not only complicates mineral processing but also poses environmental and health risks. To address these challenges, this research investigates the feasibility of utilizing Hyperspectral imaging combined with machine learning techniques for the identification of arsenic-containing minerals in copper ore samples, with a focus on practical application in sorting and processing operations. Through experimentation with various copper sulfide ores, Neighborhood Component Analysis (NCA) was employed to select essential wavelength bands from Hyperspectral data, subsequently used as inputs for machine learning algorithms to identify arsenic concentrations. Results demonstrate that by selecting a subset of informative bands using NCA, accurate mineral identification can be achieved with a significantly reduced the size of dataset, enabling efficient processing and analysis. Comparison with other wavelength selection methods highlights the superiority of NCA in optimizing classification accuracy. Specifically, the identification accuracy showed 91.9% or more when utilizing 8 or more bands selected by NCA and was comparable to hyperspectral data analysis with 204 bands. The findings suggest potential for cost-effective implementation of multispectral cameras in mineral processing operations. Future research directions include refining machine learning algorithms, exploring broader applications across diverse ore types, and integrating hyperspectral imaging with emerging sensor technologies for enhanced mineral processing capabilities.

Recent and past studies mainly focus on reducing the dead weight of structure; therefore, they considered lightweight aggregate concrete (LWAC) which reduces the dead weight but also affects the strength parameters. Therefore, the current study aims to use varied steel wire meshes to investigate the effects of LWAC on mechanical properties. Three types of steel wire mesh are used such as hexagonal (chicken), welded square, and expanded metal mesh, in various layers and orientations in LWAC. Numerous mechanical characteristics were examined, including energy absorption (EA), compressive strength (CS), and flexural strength (FS). A total of ninety prisms and thirty-three cubes were made. For the FS test, forty-five 100 × 100 × 500 mm prism samples were poured, thirty-three 150 × 150 × 150 mm cube samples were made, and forty-five 400 × 300 × 75 mm EA specimens were costed for fourteen days of curing. The experimental findings demonstrate that the FS was enhanced by adding additional forces that spread the forces over the section. One layer of chicken, welded, and expanded metal mesh enhances the FS by 52.96%, 23.76%, and 22.2%, respectively. In comparison to the remaining layers, the FS in a single-layer hexagonal wire mesh has the maximum strength, 29.49 MPa. The hexagonal wire mesh with a single layer had the greatest CS, measuring 36.56 MPa. When all three types of meshes are combined, the CS does not vary in this way and is estimated to be 29.79 MPa. In the combination of three layers, the chicken and expanded wire mesh had the most energy recorded prior to final failure, which was 1425.6 and 1108.7 J, whereas it was found the highest 752.3 J for welded square wire mesh. The energy absorption for the first layer with hexagonal wire mesh increased by 82.81% prior to the crack and by 88.34% prior to the ultimate failure. Overall, it was determined and suggested that hexagonal wire mesh works better than expanded and welded wire meshes.

Dust emissions from unpaved haul roads in open-pit coal mining pose a significant risk to air quality, health, and operational efficiency of mining operations. This study integrated real-time field monitoring with numerical simulations using ANSYS Fluent 2023 R1 to investigate the generation, dispersion, and migration of particulate matter (PM) at the Ha’erwusu open-pit coal mine under varying meteorological conditions. Real-time measurements of PM2.5, PM10, and TSP, along with meteorological variables (wind speed, wind direction, humidity, temperature, and air pressure), were collected and analyzed using Pearson’s correlation and multivariate linear regression analyses. Wind speed and air pressure emerged as dominant factors in winter, whereas wind and temperature were more influential in summer (R² = 0.391 for temperature vs. PM2.5). External airflow simulations revealed that truck-induced turbulence and high wind speeds generated wake vortices with turbulent kinetic energy (TKE) peaking at 5.02 m²/s², thereby accelerating particle dispersion. The dust migration rates reached 3.33 m/s within 6 s after emission and gradually decreased with distance. The particle settling velocities ranged from 0.218 m/s for coarse dust to 0.035 m/s for PM2.5, with dispersion extending up to 37 m downwind. The highest simulated dust concentration reached 4.34 × 10⁻² g/m³ near a single truck and increased to 2.51 × 10⁻¹ g/m³ under multiple-truck operations. Based on spatial attenuation trends, a minimum safety buffer of 55 m downwind and 45 m crosswind is recommended to minimize occupational exposure. These findings contribute to data-driven, weather-responsive dust suppression planning in open-pit mining operations and establish a validated modeling framework for future mitigation strategies in this field.