International Journal of Mining and Geo-Engineering
Year:2025 | Volume:59 | Issue:1|Papers Count:12

Recent advancements in autoencoders and their variants have notably enhanced the detection of multi-element geochemical signatures linked to ore occurences. This research employed a convolutional autoencoder algorithm (CAE) to identify geochemical anomalies, leveraging the algorithm’s ability into account the spatial correlation within the geochemical dataset. In this framework, two stream sediment datasets were generated in the Feizabad district using a conceptual modelling approach alongside a big data analysis strategy. These datasets were individually fed into the CAE model to identify multi-element geochemical anomalies based on the reconstruction error in an unsupervised manner. A comparative analysis of two geochemical prospectivity models and the simplified geological map of Feizabad demonstrates a strong spatial correlation between the identified anomaly regions and known mineral occurrences, which are distributed across andesite, tuff, and Eocene-Oligocene intrusive rocks. However, a quantitative assessment using prediction-area plots indicates that the multi-element geochemical map derived from the conceptual model exhibits a higher prediction rate (72%) compared to the geochemical prospectivity map generated through the big data approach (63%).

In this study, the displacement finite element method was employed to evaluate the load-displacement response and estimate the ultimate pullout capacity of anchor plates. A detailed comparison was conducted between conventional and non-conventional shaped single-plate and multi-plate horizontal anchors. The analysis focused on square and plus-shaped anchors, examining the influence of anchor geometry, embedment depth, plate thickness, tie rod diameter, soil relative density, and spacing between plates on their pullout performance. The results indicated that pullout capacity increases with greater relative density, plate thickness, and embedment depth but decreases with larger tie rod diameters. Square anchors demonstrated 15–40% higher pullout capacities than plus-shaped anchors due to their larger contact area. Multi-plate configurations significantly improved pullout resistance compared to single plates, with critical plate spacing optimizing performance: 1.5b for square anchors and 1b for plus-shaped anchors. For dense sand, plus-shaped multi-plate anchors exhibited comparable pullout capacities to square single-plate anchors despite a 25% reduction in anchor area. At an embedment depth of 15 m, square triple-plate anchors achieved a pullout capacity of 360.6 MPa, while plus-shaped anchors reached 256.8 MPa. Stress distribution analysis revealed localized failure patterns above the anchors, with higher stress concentrations near the plates. These findings highlighted the effectiveness of multi-plate configurations and optimized geometries in improving anchor performance, offering practical solutions for geotechnical applications requiring high pullout resistance in sandy soils. Overall, plus-shaped double-plate and triple-plate anchors can effectively replace square-shaped single-plate anchors.

In recent years, as cities expand and populations increase, the importance of public transportation, particularly subways, and underground spaces, has grown. In-situ concreting in underground areas is time-consuming, costly, and requires significant space for molding. However, shotcrete can be applied quickly with high quality and minimal space needed. The main purpose of this study is to investigate the settlement of the ground surface resulting from tunnel excavation using 3D numerical modelling. This study investigated the use of shotcrete reinforced with recycled and industrial fibers as an alternative tunnel support system in section 4 of the third phase of Tabriz metro line 2. The evaluation of the load-carrying capacity of shotcrete-lattice and fiber-reinforced shotcrete support systems showed that the maximum tensile stress for the preferred support systems is 165.1 MPa and 1.284 MPa, respectively. The results of finite element analysis revealed that shotcrete with 40 of industrial steel fibers and 30 of recycled materials can be a viable alternative to the traditional shotcrete-lattice tunnel support system in Tabriz metro line 2 in terms of resistance and surface settlement properties. The use of recycled fibers is cost-effective, and a smaller quantity of recycled fibers can provide similar mechanical properties compared to a larger quantity of industrial fibers.

Shear wave velocity (Vs) is one of the most critical parameters for determining geomechanical properties to predict reservoir behavior. Determining shear wave velocity (Vs) through methods, such as core analysis requires a significant amount of time and cost. Additionally, due to the scarcity of core samples and the heterogeneity of reservoir rocks, determining this parameter using conventional methods is often not very accurate. While many empirical methods have been developed for estimating Vs, their applicability across different regions is often limited. Therefore, estimating Vs using conventional well logs is crucial. An efficient method for predicting Vs is the use of intelligent algorithms, which offer low-cost and accurate predictions. It is feasible to predict Vs using well log data. In this study, Vs was predicted using empirical relations and some deep learning (DL) algorithms in one of the hydrocarbon fields in southern Iran. In order to use the DL methods, the autoencoders deep network was used to select the effective features in predicting the Vs, and then, with multi-layer perceptron (MLP), long-short term memory (LSTM), convolutional neural network (CNN), and convolutional neural network + long-short term memory (CNN+LSTM) networks, Vs was predicted. The performance of these models was tested by a blind data set that the models had not seen before. Furthermore, the results were checked and evaluated by set of statistical measures, including MAE, MAPE, MSE, RMSE, NRMSE, and R2 values calculated for train, test, and blind datasets. It was found that all four deep learning models used in this study well performed effectively for Vs prediction, but the combined CNN+LSTM model results indicated that the least root mean squared error (RMSE) was equal to 0.0243 (2.43%) and the best coefficient of determination (R2) equal to 0.9993 for blind dataset. We found that Vs can be predicted from a series of well log data by considering their variation trends and context information with depth by means of DL algorithms. This approach is particularly suitable for problems involving various series data, such as Vs prediction. By comparing the results obtained from DL algorithms with those from conventional empirical methods and processing real petrophysical well log data, it can be concluded that deep learning algorithms not only offer more predictive accuracy and robustness but also hold promising use prospects in Vs prediction studies. The results showed that the used CNN and CNN+LSTM networks, as new deep learning algorithms, are able to predict Vs adequately.

The tailings from mining and mineral processing have dangerous environmental effects and the reprocessing of these tailings is considered a newly emerging solution. The representative sample of the tailing dams of Mohammad Abad copper flotation plant (Markazi Province, Iran) containing 18.95% Fe2O3 was investigated for the identification and initial feasibility studies for the recovery of iron-containing minerals. Characterization studies showed that basanite, calcite, specularite, and quartz minerals were the important minerals found in the tailing dam. In the beneficiation experiments of iron minerals, the gravity beneficiation experiment did not have a good yield, but with magnetic separation with an intensity of 6000 Gauss, the grade of Fe2O3 increased up to 50.06%. Performing the reverse flotation test of calcium-containing minerals in the tailings of the magnetic separation experiment decreased the CaO grade from 23.98% to 17.07% and SO3 from 14.08% to 11.52%. The results of the feasibility tests showed that it is possible to produce iron concentrate and it is not possible to completely remove calcium and sulfur by flotation method, but the tailing of the magnetic separation (final tailing) contained 28.02% SiO2, 9.51% Fe2O3, 7.12% Al2O3, 23.98% CaO, and 14.08% SO3 and has the potential to be used in the cement industry.

The phenomenon of swelling-shrinkage has gained widespread attention in practice owing to the generation of eroded clayey layers of soil that amplify with global climate change and the seasonal water content. This provokes several serious disorders affecting the stability of nearby constructions and consequently generating human loss. The expansive clayey soils show the phenomena of wetting and drying cycles in their natural state (undisturbed soil). Hence, classical oedometric tests are found to be unable to take into account the thermal behavior of naturally swelling soils; this is proven by the resulting asymptotic volumetric behavior, as well as the steady values of the potential of swelling and shrinkage. The main aim of this experimental analysis is to derive a test that considers the significant effect of temperature. Experimental results of an oedometric approach are represented herein for the purpose of investigating the volumetric and hydric behavior of naturally swelling soil in the region of N’Gaous (Eastern Batna province, Algeria) through drying-wetting paths. Innovative expressions are derived for the direct computations of the swelling-shrinkage potential in terms of water content, appearance time and applied loads. It is of interest to mention that those expressions are applicable to other regions in the world with similar soil geotechnical and chemical characteristics and conditions. The cyclic outputs show that the swelling pressure variation with the appearance time is mainly related to the first cycle of swelling-shrinkage; as it exhibits a noticeable increase in the swelling potential with the amplification of applied loads until reaching a state of steadiness. The experimental results demonstrate a high degree of reliability and correlation with the soil behavior. Therefore, the swelling-shrinkage potentials are expressed innovatively in equations that help predict the soil behavior in expansive regions in order to enhance the safety of nearby foundations.

Due to non-uniqueness of geophysical inverse problems and measurement errors, the inversion uncertainties within the model parameters are one of the most significant necessities imposed on any modern inverse theory. Uncertainty analysis consists of finding equivalent models which sufficiently fit the observed data within the same error bound and are consistent with the prior information. In this paper, we present a non-parametric block-wise bootstrap resampling method called moving block bootstrapping (MBB) for uncertainty analysis of geophysical inverse solutions. In contrast to conventional bootstrap in which the dependence structure of data is ignored, the block bootstrap considers the dependency and correlation among the observed data by resampling not individual observations, but blocks of observations. The application of the proposed strategy to different synthetic inverse problems as well as to synthetic and real datasets of geo-electrical sounding inversion is presented. The results demonstrated that through the block bootstrap, it is possible to effectively sample the equivalence regions for a given error bound.

Interpreting core samples is a critical task in mineral exploration, essential for mine planning and design. Core Recovery (CR) and Rock Quality Designation (RQD) are key factors in assessing the geomechanical properties of a deposit during coring operations. This is particularly important in porphyry deposits, which are notable for hosting significant, deep copper mines. The accurate determination and interpretation of core recovery and RQD are crucial for these porphyry deposits. This study applied number-size (N-S) fractal modelling to enhance the interpretation of core recovery and RQD in ongoing exploratory drilling at the Sungun porphyry deposit, a prominent copper mine in Iran. Our findings revealed that core recovery and RQD exhibited a multifractal nature. Key zones for core recovery and RQD began at thresholds of 75% and 63%, respectively, with high-intensity zones for both parameters started at 89%. Additionally, the study explored correlations between these zones and other drilling parameters, such as mud flush return, drilling time, and core length, using an overall accuracy (OA) matrix. These parameters were analyzed using the N-S fractal model, indicated a strong relationship between core recovery, core length, flush returns, and drilling time. This integrative approach enhances our understanding of the deposit's geomechanical properties and guides more effective exploration strategies.

The alteration of igneous rocks indicates the formation and identification of valuable mineral deposits, such as bentonite, which is in increasing demand across various industries, including oil and steel. Remote sensing methods, leveraging the spectral characteristics of minerals, can detect hydrothermal alteration zones associated with various ore deposits, including bentonite, thereby reducing the cost of time and fieldwork. This study investigates the alteration of igneous rocks in the Khor and Biabanak region, located in the eastern part of Isfahan province, Iran, northeast of Nain city. Using ETM+ satellite data and field observations, we aimed to identify new potential bentonite resources. The ETM+ satellite data was processed using preprocessing stages including Layer Stacking, Subseting, Radiometric Corrections, Geometric Corrections, SLC-off Gap Filling, Noise Reduction (Destriping), Cloud and Water Masking, and Band Scaling/Normalization). This was followed by applying False Color Composite (FCC), Principal Component Analysis (PCA), the Enhanced Crosta technique, and the Least Squares Fitting (LS-Fit) method, which enabled us to identify promising mineral zones. Field surveys and X-ray Diffraction (XRD) analysis of samples confirmed significant concentrations of smectite (montmorillonite), indicative of substantial bentonite deposits. These findings suggest that integrating remote sensing techniques with field validation successfully identified areas with significant bentonite potential for further exploration. The successful application of these methods, particularly in a region with limited prior bentonite-focused remote sensing studies, highlights their utility in similar geological settings, offering a valuable approach for mineral exploration.

The integration of Artificial Intelligence (AI) within Mine 4.0 has significantly advanced the mining industry by enhancing performance, efficiency, safety, and overall productivity. Despite these advancements, a critical gap exists in predicting sieve refusal, a key parameter affecting grinding mill efficiency and product quality, particularly when accounting for the temporal and nonlinear dependencies inherent in mining data. This study introduces a hybrid predictive model that combines Long Short-Term Memory networks (LSTM) with Artificial Neural Networks (ANN) to predict sieve refusal in grinding mills utilizing actual process and energy data from mining industry databases. The LSTM component captured the temporal dynamics and time-delayed dependencies of variables and power consumption. Concurrently, the ANN component modeled complex, nonlinear relationships among input variables. This hybrid approach effectively addressed the intrinsic characteristics of mining data, which are often overlooked in traditional models. Comparative analyses demonstrated that the proposed LSTM-ANN model significantly outperformed existing advanced regression and deep learning methods, establishing it as a state-of-the-art solution for sieve refusal prediction. The enhanced predictive accuracy provided direct support for operational planning and scheduling, contributing to improved energy efficiency and cost-effectiveness in mining operations. By addressing the underexplored temporal and spatial interrelations between variables and sieve refusal, this research fills a notable gap in the application of deep learning to grinding mill operations. The findings underscore the transformative potential of advanced AI models in optimizing mining practices, aligning with the broader objectives of Mine 4.0 to leverage intelligent data analysis for operational excellence.

This study presents the implementation of an automatic inversion algorithm designed for the analysis of direct current (DC) vertical electrical sounding (VES) data, utilizing a one-dimensional (1D) linear integral equation approach. The forward modelling problem was derived from a three-dimensional (3D) integral equation, which was elegantly simplified through numerical integration across horizontal dimensions. The inverse problem was tackled through a minimum length solution that integrated a depth-weighting function and optimized the regularization parameter based on the maximum value of the forward operator. The efficacy of this algorithm was validated by inverting synthetic datasets as well as by its application to real field data. The results highlighted the limitations inherent in 1D inversion, particularly in cases where a layered Earth is significantly violated, as evidenced by comparisons with two-dimensional inversion models. In contrast, in contexts characterized by predominantly layered subsurface structures, the algorithm successfully produced accurate representations of the subsurface models. These findings underscore the method's efficacy in various geological environments, offering a robust tool for geophysical exploration.

The escalating contamination of global water resources from industrial, agricultural, and domestic effluents underscores the urgent need for innovative wastewater treatment strategies. Metal-based nanoparticles (NPs) have revolutionized water purification because of their large surface area, strong reactivity, and adjustable physicochemical properties. This review explores the applications of NPs, such as zinc, iron, silver, titanium dioxide, cerium oxide, manganese oxide, and magnesium oxide in removing heavy metals, dyes, organic pollutants, and microbial pathogens from wastewater. The key mechanisms, including adsorption, filtration, photocatalysis, and redox reactions were critically analyzed, highlighting their superior efficiency in pollutant removal and water purification. The review also emphasized recent advancements in hybrid nanocomposites and functionalized NPs, which enhance selectivity and removal performance. Factors, such as nanoparticle size, surface charge, pH, and contact time influencing pollutant removal efficiency. Photocatalysis and redox mechanisms stand out for their eliminating complex pollutants into non-toxic byproducts, making them invaluable in addressing bioaccumulation and environmental risks. Despite these promising advancements, challenges persist, including potential nanoparticle toxicity, environmental persistence, and the scalability of these technologies. Future research should prioritize green synthesis methods, cost-effective production, and long-term environmental impact assessments. Integrating NPs with advanced treatment technologies, such as membrane filtration and oxidation processes, could offer a sustainable and scalable solution to global water scarcity and pollution. This review underscores the critical role of nanotechnology in developing efficient, eco-friendly wastewater treatment systems to ensure water security and environmental sustainability.