Grade Prediction of an Indian Iron Ore Mining using Machine Learning and Ensemble Models | ||
| Journal of Mining and Environment | ||
| مقاله 9، دوره 17، شماره 2، خرداد و تیر 2026، صفحه 531-544 اصل مقاله (2.82 M) | ||
| نوع مقاله: Original Research Paper | ||
| شناسه دیجیتال (DOI): 10.22044/jme.2025.16430.3208 | ||
| نویسندگان | ||
| Tapan Dey* 1؛ Gopinath Samanta2 | ||
| 1Research Scholar, Mining Engineering, NIT Rourkela, Kolkata, India | ||
| 2Senior Technologist, Tata Steel Ltd., Jamshedpur, India | ||
| چکیده | ||
| Accurate grade prediction is an important step in the mining planning process. Various methods, namely the Inverse Distance Method and Kriging, are widely used. The application of machine learning is a new development in the grade estimation technique. The present study focused on the application of XGBoost, Random Forests (RFs), Multi Layer Perceptron (MLP), and Gradient Boosting Regression (GBR) models to predict iron ore grades in an Indian mine. An ensemble model was also applied to obtain a more stable grade prediction in the deposit. Models were trained using 4,112 sample data, which have spatial coordinates (east, north, and altitude) and iron grades. The dataset was divided into two parts: 80% (3,289 samples) of the data was used for model training, and 20% (823 samples) was used for model testing. The performance of the models was assessed through the coefficient of determination (R²), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). The results show that the XGBoost model performs better in the estimation process when compared with other methods, such as RFs, GBR, and MLP. The XGBoost model produced R² of 0.77, MSE of 2.87, and MAPE of 1.8%. The findings indicate that the XGBoost model is effective for predicting iron ore grades in this type of deposit. However, considering geological uncertainty, the application of an ensemble model may be beneficial for grade prediction in an iron deposit. | ||
| کلیدواژهها | ||
| ML؛ Krigging؛ XGboost؛ Random Forests؛ Estimation | ||
| مراجع | ||
|
[1]. Sinclair, A., & Blackwell, G. (2002). Applied mineral inventory estimation. UK Cambridge. Univ Press, Cambridge, 400.
[2]. Rendu, J. (2014). An Introduction to Cut-Off Grade Estimation. Society for Mining, Metallurgy, and Exploration.
[3]. Kaplan, U., & Topal, E. (2020). A new ore grade estimation using combine machine learning algorithms. Minerals, 10, 847.
[4]. Kapageridis, I., & Denby, B. (1999). Ore Grade Estimation with Modular Neural Network Systems - A Case Study.
[5]. Yamamoto, J. (1999). Quantification of uncertainty in ore-reserve estimation: applications to Chapada copper deposit. State of Goias, Brazil. Natural Resources Research, 8, 153–163.
[6]. Wu, X., & Zhou, Y. (1993). Reserve estimation using neural network techniques. Computer Geoscience, 19, 567–575.
[7]. Kapageridis, I., & Denby, B. (1998). Neural network modelling of ore grade spatial variability, International Conference on Artificial Neural Networks. Springer, Bratislava, Slovakia, 209–214.
[8]. Zimmerman, D., Pavlik, C., Ruggles, A., & Armstrong, M. (1999). An experimental comparison of ordinary and universal kriging and inverse distance weighting. Mathematics Geology, 31, 375–390.
[9]. Mahmoudabadi, H., Izadi, M., & Menhaj, M. (2009). A hybrid method for grade estimation using genetic algorithm and neural networks. Computer Geoscience, 13, 91–101.
[10]. Jafrasteh, B., Fathianpour, N., & Suárez, A. (2018). Comparison of machine learning methods for copper ore grade estimation. Computer Geoscience, 22, 1371–1388.
[11]. Kaplan, U., Dagasan, Y., & Topal, E. (2021). Mineral grade estimation using gradient boosting regression trees. International Journal of Mining, Reclamation and Environment, 35, 728-742.
[12]. Bertolini, M., Mezzogori, D., Neroni, M., & Zammori, F. (2021). Machine Learning for industrial applications: A comprehensive literature review. Expert Systems with Applications, 175.
[13]. Jung, D., & Choi, Y. (2021). Systematic review of machine learning applications in mining: Exploration, exploitation, and reclamation. Minerals (Basel, Switzerland), 11, 148.
[14]. Atalay, F. (2024). Estimation of Fe Grade at an Ore Deposit Using Extreme Gradient Boosting Trees (XGBoost). Mine Metallurgy Exploration, 41, 2119–2128.
[15]. Salarian, S., Oskooi, B., Mostafaei, K., & Smirnov, M. (2024). Improving the resource modeling results using auxiliary variables in estimation and simulation methods. Earth Science Informatics, 17, 4161–4181.
[16]. Mostafaei, K. & 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, 857-872.
[17]. Mostafaei, K., Maleki, S., Shokri, B., & Yousefi, M. (2023). Predicting gold grade using support vector machine and neural network to generate an evidence layer for 3D prospectivity analysis. International Journal of Mining and Geo-Engineering, 57, 435-444.
[18]. Mostafaei, K. & 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.
[19]. Kianoush, P., Afzal, P., Mohammadi, G., Khah, N., & Hosseini, S. (2023). Application of geostatistical and velocity-volume fractal models to determine interval velocity and formation pressures in an oilfield of SW Iran. Journal of Petroleum Research, 33 (1402-1), 146-170.
[20]. Sotoudeh F., Ataei M., Kakaie R., & Pourrahimian Y. (2020). Application of Sequential Gaussian Conditional Simulation into Underground Mine Design under Grade Uncertainty. Journal of Mining and Environment, 11 (3), 695-709.
[21]. Tahernejad M.M., Khalokakaie R., & Ataei M. (2018). Analyzing the effect of ore grade uncertainty in open pit mine planning; A case study of Rezvan iron mine, Iran. Int. Journal of Mining and Geo-Engineering, 52 (1), 53-60.
[22]. Monjezi M., Rajabalizadeh Kashani M. & Ataei M. (2013). A comparative study between sequential Gaussian simulation and kriging method grade modeling in open-pit mining. Arabian Journal of Geosciences, 6 (1), 123-128.
[23]. Sohrabian, B., & Tercan, E. (2025). Grade Estimation Through the Gaussian Copulas: A Case Study. Journal of Mining and Environment, 16(1), 1-13.
[24]. Parhizkar A., Ataei M., Moarefvand P., & Rasouli V. (2011). Grade Uncertainty and its Impact on Ore Grade Reconciliation between the Resource Model and the Mine. Archives of Mining Science, 56 (1), 119–134.
[25]. Parhizkar A., Ataei M., Moarefvand P., & Rasouli V. (2012). A Probabilistic Model to Improve Reconciliation of Estimated and Actual Grade in Open Pit Mining. Arabian Journal of Geosciences, 5 (6), 1279-1288.
[26]. Fathi, M., Alimoradi, A., & Hemati Ahooi, H. R. (2021). Optimizing extreme learning machine algorithm using particle swarm optimization to estimate iron ore grade. Journal of Mining and Environment, 12 (2), 397-411.
[27]. Ghasemitabar, H., Alimoradi, A., Hemati Ahooi, H., & Fathi, M. (2024). Intelligent Borehole Simulation with python Programming. Journal of Mining and Environment, 15(2), 707-730.
[28]. Singh, R., Sarkar, B., & Ray, D. (2021). Geostatistical modelling of a high-grade iron ore deposit. Journal of the Geological Society of India, 97, 1005–1012.
[29]. Criminisi, A., Shotton, J., & Konukoglu, E. (2012). Decision forests: a unified approach to classification, regression, density estimation, manifold learning, and semi-supervised learning. Computer Graphics and Vision, 7.
[30]. Trehan, S., Carlberg, K., & Durlofsky, L. (2017). Error modeling for surrogates of dynamic systems using machine learning. International Journal for Numerical Methods in Engineering.
[31]. Delgado, F., Cernadas, E., Barro, S., & Amorim, D. (2014). Is it necessary to have hundreds of classifiers to tackle real-world classification challenges? Journal of Machine Learning Research, 15, 3133-3181.
[32]. Friedman, J. (2001). Greedy boosting approximation: A gradient boosting machine. Annals of Statistics, 29, 1189-1232.
[33]. Batlile, N., Adachi, T., & Kawamura, Y. (2023). Utilization of Artificial Neural Networks in Predicting Copper Ore Grade. Minerals, 13.
[34]. Daya Sagar, B. S., Cheng, Q., & Agterberg, F. (Eds.). (2018). Handbook of mathematical geosciences: Fifty years of IAMG. Springer International Publishing.
[35]. Griffith, D. (2015). Spatial Statistics and Geostatistics: Basic Concepts. In: Shekhar, S., Xiong, H., Zhou, X. (eds) Encyclopedia of GIS. Springer, Cham.
[36]. Rossi, M. E., & Deutsch, C. V. (2014). Mineral Resource Estimation. New York: Springer.
[37]. Kaplan, U., & Topal, E. (2020). A new ore grade estimation using combine machine learning algorithms, Minerals, 10.
[38]. Atalay, F. (2024). Estimation of fe grade at an ore deposit using extreme gradient boosting trees (XGBoost). Mining, Metallurgy & Exploration, 41, 2119-2128.
[39]. Chatterjee, S., Bandopadhyay, S., & Machuca, D. (2010). Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model. Mathematical Geosciences, 42, 309-326. | ||
|
آمار تعداد مشاهده مقاله: 147 تعداد دریافت فایل اصل مقاله: 105 |
||