Exploration
Jairo Jhonatan Marquina Araujo; Marco Antonio Cotrina Teatino; José Nestor Mamani Quispe; Eduardo Manuel Noriega Vidal; Juan Antonio Vega Gonzalez
Abstract
The objective of this research work to employ machine learning techniques including Multilayer Perceptron Artificial Neural Networks (ANN-MLP), Random Forests (RFs), Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) to predict copper ore grades in a copper deposit located in Peru. ...
Read More
The objective of this research work to employ machine learning techniques including Multilayer Perceptron Artificial Neural Networks (ANN-MLP), Random Forests (RFs), Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) to predict copper ore grades in a copper deposit located in Peru. The models were developed using 5654 composites containing available geological information (rock type), as well as the locations of the samples (east, north, and altitude) and secondary ore grade (Mo) obtained from drilling wells. The data was divided into 10% (565 composites) for testing, 10% (565 composites) for validation, and 80% (4523 composites) for training. The evaluation metrics included SSE (Sum of Squared Errors), RMSE (Root Mean Squared Error), NMSE (Normalized Mean Squared Error), and R² (Coefficient of Determination). The XGBoost model could predict the ore grade with an SSE of 15.67, RMSE = 0.17, NMSE = 0.34, and R² = 0.66, the RFs model with an SSE of 16.40, RMSE = 0.17, NMSE = 0.36, and R² = 0.65, the SVR model with an SSE of 19.94, RMSE = 0.19, NMSE = 0.43, and R² = 0.57, and the ANN-MLP model with an SSE = 21.00, RMSE = 0.19, NMSE = 0.46, and R² = 0.55. In conclusion, the XGBoost model was the most effective in predicting copper ore grades.
Exploitation
Hassanreza Ghasemitabar; Andisheh Alimoradi; Hamidreza Hemati Ahooi; Mahdi Fathi
Abstract
Drilling of exploratory boreholes is one of the most important and costly steps in mineral exploration, which can provide us with accurate and appropriate information to continue the mining process. There are limitations on drilling the target boreholes, such as high costs, topographical problems in ...
Read More
Drilling of exploratory boreholes is one of the most important and costly steps in mineral exploration, which can provide us with accurate and appropriate information to continue the mining process. There are limitations on drilling the target boreholes, such as high costs, topographical problems in installation of drilling rigs, restrictions caused by previous mining operation etc. The advances in artificial intelligence can help to solve these problems. In this research, we used python as one of the most pervasive and the most powerful programming languages in the field of data analysis and artificial intelligence. In this method mean shift algorithms have been used to cluster data, random forest to estimate clusters, and gradient boosting to estimate iron grade. Finally, in the studied area of Choghart in Central Iran, more than 91% accuracy was achieved in detection of ore blocks. Also, the results of the neural network indicate the mean square error (MSE) and mean absolute error (MAE) in the training data, respectively equal to 0.001 and 0.029, in the test data is 0.002 and 0.03, and in the validation boreholes, we reached a maximum of 0.06 and 0.2.
M. P. Sadr; M. Nazeri
Abstract
The Dolatabad area located in SE Iran is a well-endowed terrain owning several chromite mineralized zones. These chromite ore bodies are all hosted in a colored mélange complex zone comprising harzburgite, dunite, and pyroxenite. These deposits are irregular in shape, and are distributed as small ...
Read More
The Dolatabad area located in SE Iran is a well-endowed terrain owning several chromite mineralized zones. These chromite ore bodies are all hosted in a colored mélange complex zone comprising harzburgite, dunite, and pyroxenite. These deposits are irregular in shape, and are distributed as small lenses along colored mélange zones. The area has a great potential for discovering further chromite resources. Therefore, the current work endeavors to delineate the favorable zones of podiform chromite mineralization to focus on the detailed exploration surveys. In order to achieve this goal, the machine learning random forests algorithm was adapted to integrate the footprints of mineralization in various exploration datasets. The genetic characteristics of podiform chromite deposits were used to define the exploration criteria. These defined criteria were then translated to a set of exploration evidence layers. The competent exploration evidence layers, i.e. those with remarkable positive spatial associations with mineralization, were then recognized using distance distribution analysis. Respecting the location of known chromite mineralizations and competent exploration evidence layers, a predictive random forests model was trained and then applied to predict the favorable zones of chromite prospectivity. The delineated targets were found to occupy 19% of the studied area, in which all the known chromite mineralizations were delimited. Consequently, it is worthy to follow up the detailed exploration surveys within the delineated zones.
