Copper Ore Grade Prediction using Machine Learning Techniques in a Copper Deposit

Marquina Araujo, Jairo Jhonatan; Cotrina Teatino, Marco Antonio; Mamani Quispe, José Nestor; Noriega Vidal, Eduardo Manuel; Vega Gonzalez, Juan Antonio; Vega-Gonzalez, Juan; Cruz-Galvez, Juan

doi:10.22044/jme.2024.14032.2617

Document Type : Original Research Paper

Authors

¹ Department of Mining Engineering, Faculty of Engineering, National University of Trujillo, Trujillo, Peru

² Department of Chemical Engineering, Faculty of Engineering, National University of the Altiplano of Puno, Puno, Perú

³ Departamento de Ingeniería Metalurgica, Universidad Nacional de Trujillo, Trujillo, Perú

⁴ Department of Metallurgical Engineering, Faculty of Engineering, National University of Trujillo, Trujillo, Perú

https://doi.org/10.22044/jme.2024.14032.2617

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. 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.

Keywords

Main Subjects

Geostatistics

References

[1]. Reza, M. and Aghajani, A. (2019). Cutoff grades optimization in open pit mines using meta-heuristic algorithms. Resources Policy, 60, 72-82.

[2]. Batlile, N., Adachi, T., and Kawamura, Y. (2023). Application of Artificial Neural Network for the Prediction of Copper Ore Grade. Minerals, 13 (5).

[3]. Battalgazy, N., Valenta, R., Gow, P., Spier, C., and Forbes, G. (2023). Addressing Geological Challenges in Mineral Resource Estimation: A Comparative Study of Deep Learning and Traditional Techniques. Minerals, 13(7).

[4]. Alimoradi, A., Maleki, A., Karimi, M., Sahafzadeh, S., and Abbasi. (2020). Integrating Geophysical Attributes with New Cuckoo Search Machine Learning Algorithm to Estimate Silver Grade Values–Case Study: Zarshouran Gold Mine. Journal of Mining and Environment (JME), 11 (3), 865-879.

[5]. Zhang, S., Nwaila, G., Bourdeau, J., Ghorbani, Y., and Carranza, E. (2023). Machine Learning-based Delineation of Geodomain Boundaries: A Proof-of-Concept Study using Data from the Witwatersrand Goldfields. Natural Resources Research, 32, 879-900.

[6]. Deutsch, J., Szymanski, J., and Deutsch, C. (2014). Checks and measures of performance for kriging estimates. Journal of the Southern African Institute of Mining and Metallurgy, 114 (3).

[7]. Ro, Y. and Yoo, C. (2022). Numerical Experiments Applying Simple Kriging to Intermittent and Log-Normal Data. Water, 14 (9).

[8]. Park, N., Kyriakidis, P., and Young, S. (2016). Spatial Estimation of Classification Accuracy Using Indicator Kriging with an Image-Derived Ambiguity Index. Remote Sens, 8 (4).

[9]. Giraldo, R., Delicado, P., and Mateu, J. (2011). Ordinary kriging for function-valued spatial data. Environmental and Ecological Statistics, 18, 411-426.

[10]. Dumakor-Dupey, N. and Arya, S. (2021). Machine Learning—A Review of Applications in Mineral Resource Estimation. Energies, 14, 4079.

[11]. Ghasemitabar, H., Alimoradi, A., Hemati, H., and Fathi, M. (2024). Intelligent Borehole Simulation with python Programming. Journal of Mining and Environment, 15 (2), 707-730.

[12]. Lloyd, C. and Atkinson, P. (2001). Assessing uncertainty in estimates with ordinary and indicator kriging. Computers & Geosciences, 27 (8), 929-937.

[13]. Gia, T., Kappas, M., Van, C., and Khanh, L. (2019). Application of Ordinary Kriging and Regression Kriging Method for Soil Properties Mapping in Hilly Region of Central Vietnam. ISPRS Int. J. Geo-Inf, 8 (3).

[14]. Emrah, U. and Topal, E. (2020). A New Ore Grade Estimation using Combine Machine Learning Algorithms. Minerals, 10 (10).

[15]. Li, X., Xie, Y., Guo, Q., and Li, L. (2010). Adaptive ore grade estimation method for the mineral deposit evaluation. Mathematical and Computer Modelling, 52 (11-12), 1947-1956.

[16]. Chatterjee, S., Bandopadhyay, S., and Machuca, D. (2010). Ore Grade Prediction using a Genetic Algorithm and Clustering-based Ensemble Neural Network Model. Mathematical Geosciences, 42 (3), 309-326.

[17]. Guerra, C., Souza, C., and Muico, E. (2023). Ore-Grade Estimation from Hyperspectral Data using Convolutional Neural Networks: A Case Study at the Olympic Dam Iron Oxide Copper-Gold Deposit, Australia. Economic Geology, 118 (8), 1899-1921.

[18]. Nagpal, G., Shrikant, S., Krishna, N., Nagpal, A., and Mohan, G. (2022). Ore Grade Estimation in Mining Industry from petro-physical data using neural networks. ICIMMI '22: Proceedings of the 4th International Conference on Information Management & Machine Intelligence, 75, 1-5.

[19]. Mostafaei, K. and Ramazi, H. (2018). 3D model construction of induced polarization and resistivity data with quantifying uncertainties using geostatistical methods and drilling (Case study: Madan Bozorg, Iran). Journal of Mining & Environment, 9 (4), 857-872.

[20]. Mostafaei, K. and Ramazi, H. (2019). Mineral resource estimation using a combination of drilling and IP-Rs data using statistical and cokriging methods. Bulletin of the Mineral Research and Exploration, 160, 177-195.

[21]. Jafrasteh, B., Fathianpour, N., and Suárez, A. (2018). Comparison of machine learning methods for copper ore grade estimation. Comput Geosci, 22, 1371-1388.

[22]. Hekmantnejad, A., Emery, X., and Alipour, M. (2019). Comparing linear and non-linear kriging for grade prediction and ore/waste classification in mineral deposits. International Journal of Mining, Reclamation and Environment, 33 (4).

[23]. Goswami, A., Mishra, M., and Patra, D. (2022). Evaluation of machine learning algorithms for grade estimation using GRNN & SVR. Engineering Research Express, 4 (3).

[24]. Fathi, M., Alimoradi, A., and Hemati, H. (2021). Optimizing Extreme Learning Machine Algorithm using Particle Swarm Optimization to Estimate Iron Ore Grade. Journal of Mining and Environment (JME), 12 (2), 397-411.

[25]. Alimoradi, A., Hajkarimian, H., Hemati, H., and Salsabili, M. (2022). Comparison between the performances of four metaheuristic algorithms in training a multilayer perceptron machine for gold grade estimation. International Journal of Mining and Geo-Engineering, 56 (2), 97-105.

[26]. Sarantsatsral, N., Ganguli, R., Pothina, R., and Tumen, B. (2021). A Case Study of Rock Type Prediction using Random Forests: Erdenet Copper Mine, Mongolia. Minerals, 11 (10).

[27]. Afzal, P., Farhadi, S., Boveiri, M., Shamseddin, M., and Daneshvar, L. (2022). Geochemical Anomaly Detection in the Irankuh District using Hybrid Machine Learning Technique and Fractal Modeling. Geopersia, 12 (1), 191-199.

[28]. Patel, A., Chatterjee, S., and Gorai, A. (2019). Development of a machine vision system using the support vector machine regression (SVR) algorithm for the online prediction of iron ore grades. Earth Sci Inform, 12, 197-210.

[29]. Farhadi, S., Afzal, P., Boveiri, M., Daneshvar, L., and Sadeghi, B. (2022). Combination of Machine Learning Algorithms with Concentration-Area Fractal Method for Soil Geochemical Anomaly Detection in Sediment-Hosted Irankuh Pb-Zn Deposit, Central Iran. Minerals, 12 (6), 689.

[30]. Xie, J., Wang, Q., Liu, P., and Li, Z. (2021). A hyperspectral method of inverting copper signals in mineral deposits based on an improved gradient-boosting regression tree. International Journal of Remote Sensing, 42 (14), 5474-5492.

[31]. Sola, J. and Sevilla, J. (1997). Importance of input data normalization for the application of neural networks to complex. IEEE Trans. Nucl. Sci, 44, 1464-1468.

[32]. Larsen, R. and Marx, M. (2005). An Introduction to Mathematical Statistics and its Applications, UK: Prentice Hall: London.

[33]. Singh. D. and Singh, B. (2019). Investigating the impact of data normalization on classification performance. Appl. Soft Comput., 105524.

[34]. Irie, B. and Miyake, S. (1988). Capabilities of three-layered perceptrons. In: IEEE International Conference on Neural Networks, 1988, 641-648.

[35]. Gomes, G., Ludermir, T., and Lima, L. (2011). Comparison of new activation functions in neural network for forecasting financial time series. Neural Comput. Applic, 20 (3), 417-439.

[36]. Criminisi, A., Shotton, J., and Konukoglu, E. (2012). Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Computer Graphics and Vision, 7 (223), 81-227.

[37]. Trehan, S., Carlberg, K., and Durlofsky, L. (2017). Error modeling for surrogates of dynamical systems using machine learning. International Journal for Numerical Methods in Engineering.

[38]. Fernández-Delgado, M., Cernadas, E., Barro, S., and Amorim, D. (2014). Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learn. Res, 15, 3133-3181.

[39]. Ho, T. (1998). The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell, 20 (8), 832-844.

[40]. Breiman, L. (1996). Bagging predictors. Mach. Learn, 24 (2), 123-140.

[41]. Friedman, J. (2001). Greedy boosting approximation: A gradient boosting machine. Annal. Stat, 29 (5), 1189-1232.

[42]. Breiman, L., Friedman, J., and Olshen, R. (1984). Classification and regression trees. Wadsworth int, Group, 37 (15), 237-251.

[43]. Song, K., Yan, F., and Ding, T. (2020). A steel property optimization model based on the xgboost algorithm and improved pso. Comput. Mater. Sci, 174, 109472.

[44]. Krizhevsky, A., Sutskever. I., and Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 1097-1105.

[45]. Emrah, U., Dagasan, Y., and Topal, E. (2021). Mineral grade estimation using gradient boosting regression trees. International Journal of Mining, Reclamation and Environment, 35 (10), 728-742.

[46]. Rivas-Perea, P., Cota-Ruiz, J., Chaparro, D., Venzor, J., Carreón, A., and Rosiles, J. (2013). Support vector machines for regression: a succinct review of large-scale and linear programming formulations. Int J Intell Sci, 3, 5-14.

[47]. Prasad, K., Gorai, A., and Goyal, P. (2016). Development of ANFIS models for air quality forecasting and input optimization for reducing the computational cost and time. Atmos Environ, 128, 246-262.

Copper Ore Grade Prediction using Machine Learning Techniques in a Copper Deposit

References

References

Volume 15, Issue 3May 2024Pages 1011-1027

Volume 15, Issue 3
May 2024
Pages 1011-1027