Exploration
Hassanreza Ghasemi Tabar; Andisheh Alimoradi; mahdi fathi; Maryam Sahafzadeh
Abstract
Estimating ore grades during the exploration phase is often time-consuming and costly due to the need for extensive drilling. Geophysical surveys, as the last indirect exploration method before drilling, offer valuable insights into subsurface mineralization. This study introduces a novel approach for ...
Read More
Estimating ore grades during the exploration phase is often time-consuming and costly due to the need for extensive drilling. Geophysical surveys, as the last indirect exploration method before drilling, offer valuable insights into subsurface mineralization. This study introduces a novel approach for simulating “identical twins” of borehole copper grade values using geophysical attributes derived from the geoelectrical method in the Kahang porphyry copper deposit, central Iran. By treating the simulated values as digital twins of actual borehole grades, we employed four machine learning algorithms—Linear Regression (LR), Gradient Boosting (GB), Random Forest (RF), and Support Vector Machine (SVM)—to model the complex relationships between geophysical inputs and copper grades. After data preprocessing with Principal Component Analysis (PCA), a refined dataset was used to train, test, and validate each model. The results demonstrate that GB yielded the highest predictive accuracy, generating grade estimates closely aligned with actual values. This identical twin modeling approach highlights the potential of machine learning to enhance early-stage mineral exploration by reducing dependence on costly drilling.
Exploration
Marco Antonio Cotrina-Teatino; Jairo Jhonatan Marquina-Araujo; Jose Nestor Mamani-Quispe; Solio Marino Arango-Retamozo; Johnny Henrry Ccatamayo-Barrios; Joe Alexis Gonzalez-Vasquez; Teofilo Donaires-Flores; Maxgabriel Alexis Calla-Huayapa
Abstract
This work aimed to categorize mineral resources in a copper deposit in Peru, using a machine learning model, integrating the K-prototypes clustering algorithm for initial classification and Random Forest (RF) as a spatial smoother. A total of 318,443 blocks were classified using geostatistical and geometric ...
Read More
This work aimed to categorize mineral resources in a copper deposit in Peru, using a machine learning model, integrating the K-prototypes clustering algorithm for initial classification and Random Forest (RF) as a spatial smoother. A total of 318,443 blocks were classified using geostatistical and geometric variables derived from Ordinary Kriging (OK) such as kriging variance, sample distance, number of drillholes, and geological confidence. The model was trained and validated using precision, recall, and F1-score metrics. The results indicated an overall accuracy of 97%, with the measured category achieving 98% precision and an F1-score of 0.98. The total estimated tonnage was 5,859.36 Mt, distributed as follows: 1,446.13 Mt (measured), 2,249.22 Mt (Indicated), and 2,164.01 Mt (Inferred), with average copper grades of 0.43%, 0.33%, and 0.31% Cu, respectively. Compared to the traditional geostatistical methods, this hybrid approach improves classification objectivity, spatial continuity, and reproducibility, minimizing abrupt transitions between categories. The RF model proved to be a robust tool, reducing classification inconsistencies and better capturing geological uncertainty. Future studies should explore hybrid models (K-means with RF, ANN with K-Prototypes, gradient boosting, and deep learning) and incorporate economic variables to optimize decision-making in resource estimation.
Rock Mechanics
Arun Kumar Sahoo; Debi Prasad Tripathy; Singam Jayanthu
Abstract
The mining industry needs to accept new-age autonomous technologies and intelligent systems to stay up with the modernization of technology, to benefit the shake of investors and stakeholders, and most significantly, for the nation, and to protect health and safety. An essential part of geo-technical ...
Read More
The mining industry needs to accept new-age autonomous technologies and intelligent systems to stay up with the modernization of technology, to benefit the shake of investors and stakeholders, and most significantly, for the nation, and to protect health and safety. An essential part of geo-technical engineering is doing slope stability analysis to determine the likelihood of slope failure and how to prevent it. A reliable, cost-effective, and generally applicable technique for evaluating slope stability is urgently needed. Numerous research studies have been conducted, each employing a unique strategy. An alternate method that uses machine learning (ML) techniques is to study the relationship between stability conditions and slope characteristics by analyzing the data collected from slope monitoring and testing. This paper is an attempt by the authors to comprehensively review the literature on using the ML techniques in slope stability analysis. It was found that most researchers relied on data-driven approaches with limited input variables, and it was also verified that the ML techniques could be utilized effectively to predict slope failure analysis. SVM and RF were the most popular types of ML models being used. RMSE and AUC were used extensively in assessing the performance of the ML models.
Exploration
N. Mahvash Mohammadi; A. Hezarkhani
Abstract
Identification and mapping of the significant alterations are the main objectives of the exploration geochemical surveys. The field study is time-consuming and costly to produce the classified maps. Therefore, the processing of remotely sensed data, which provide timely and multi-band (multi-layer) data, ...
Read More
Identification and mapping of the significant alterations are the main objectives of the exploration geochemical surveys. The field study is time-consuming and costly to produce the classified maps. Therefore, the processing of remotely sensed data, which provide timely and multi-band (multi-layer) data, can be substituted for the field study. In this study, the ASTER imagery is used for alteration classification by applying two new methods of machine learning, including Random Forest and Support Vector Machine. The 14 band ASTER and 19 derivative data layers extracted from ASTER including band ratio and PC imagery, are used as training datasets for improving the results. Comparison of analytical results achieved from the two mentioned methods confirmed that the SVM model has sufficient accuracy and more powerful performance than RF model for alteration classification in the study area.
