Sample’s location

Publicado

2025-01-27

Estimation of emerald mineralization probability using machine learning algorithms

Estimación de la probabilidad de mineralización de esmeraldas usando algoritmos de aprendizaje automático

DOI:

https://doi.org/10.15446/dyna.v92n235.112504

Palabras clave:

gems, calibration, drillhole, mineral target (en)
gemas, calibración, perforación, objetivo minero (es)

Descargas

Autores/as

This research proposes a machine learning (ML) model that estimates the probability of emerald mineralization in rocks of the Western Emerald Belt (CEOC). Element concentrations, lithologies and coordinates were used as input variables and productivity as the target variable (176 samples). The variables were transformed to be integrated into the model. (1) Variable selection was performed using the Boruta method and backward elimination. (2) A logistic regression, a neural network, and a support vector machine were trained. (3) Calibration was achieved with the Platt method. (4) Calibration assessment was conducted by using the Brier score and calibration curves. The model selected was a calibrated support vector machine (C = 0.19 and λ = 0.1) that included 17 geochemical variables and the coordinates. The results were presented in a 3D plot. Assigning a probability value to each sample allows the mining targets to be ranked.

La investigación propone un modelo de aprendizaje automático para estimar la probabilidad de mineralización de esmeraldas en el Cinturón Esmeraldífero Occidental (CEOC). Se emplearon concentraciones elementales, litología y coordenadas como variables de entrada y la productividad como variable objetivo (176 muestras). Las variables fueron transformadas para ser integradas al modelo. (1) Se recurrió a los métodos Boruta y backward elimination para seleccionar las variables. (2) Una regresión logística (LR), una red neuronal de retropropagación (BPNN) y una máquina de vectores de soporte (SVM) fueron entrenadas. (3) Se usó la calibración de Platt y (4) se evaluó su desempeño usando la puntuación Brier y curvas de calibración. El modelo elegido fue una máquina de vectores de soporte calibrada (C = 0.19 y λ = 0.1) que incluyó 17 variables geoquímicas y las coordenadas. Asignar valores de probabilidad permitió jerarquizar los objetivos mineros.

Referencias

[1] Cartier, L.E., Gemstones and sustainable development: perspectives and trends in mining, processing and trade of precious stones. Extr Ind Soc. 6(4), pp. 1013-1016, 2019. DOI: https://doi.org/10.1016/j.exis.2019.09.005

[2] Agencia Nacional Minera - Unidad de planeación minero-energética UPME. Producción histórica de esmeraldas en Colombia. [online]. 2021.

[3] Dominy, S.C., Noppé, M.A., and Annels, A.E., Errors and uncertainty in mineral resource and ore reserve estimation: the importance of getting it right. [online]. 2004. Available at: https://bit.ly/3os0e4M. DOI: https://doi.org/10.2113/11.1-4.77

[4] Quintín, J., Estudios de la estimación y simulación geoestadística para la caracterización de parámetros geólogo-industriales en el yacimiento laterítico Punta Gorda. Minería y Geología. 21, 2005.

[5] Niño, G., and Sheng-Rong, S., Geological and geochemical analyses for emerald exploration in the Muzo Formation along the Western Emerald Belt, Colombia. National Taiwan University, 2017.

[6] Melo, R.T., Notas sobre el contexto tectonoestratigráfico de formación de las esmeraldas colombianas. Boletín Geológico. 45(45), pp. 37-48, 2019. DOI: https://doi.org/10.32685/0120-1425/boletingeo.45.2019.486

[7] Moreno, G., Terraza, R., Montoya, D., Geología del cinturón esmeraldífero oriental. Boletín de Geología. [online]. 31, pp. 51-67, 2009. Available at: https://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S0120-02832009000200004&nrm=iso

[8] Pignatelli, I., Guiliani, G., Ohnenstetter, D., et al., Colombian Trapiche Emeralds: recent advances in understanding their formation. Gems & Gemology. 51, pp. 222-259, 2015. DOI: https://doi.org/10.5741/gems.51.3.222

[9] Groat, L.A., Giuliani, G., Marshall, D.D., Turner, D., Emerald deposits and occurrences: a review. Ore Geol Rev. 34(1-2), pp. 87-112, 2008. DOI: https://doi.org/10.1016/j.oregeorev.2007.09.003

[10] Mendoza, J., Anotaciones geoquímicas para exploración de esmeraldas en la región Muzo-Coscuez con base en la relación Na/K y elementos traza. Geología Colombiana. 21, pp. 89-98, 1996.

[11] Ottaway, T.L., The geochemistry of the Muzo emerald deposit, Colombia. University of Toronto, Toronto, Canada, 1991, 216 P.

[12] Ochoa, L.H., Evaluación magnetometría, radiométrica y geoeléctrica de depósitos esmeraldíferos. Geofísica Colombiana. 7, pp. 13-18, 2003.

[13] Dumakor-Dupey, N.K., and Arya, S., Machine learning—a review of applications in mineral resource estimation. Energies (Basel). 14(14), art. 4079, 2021. DOI: https://doi.org/103390/en14144079

[14] Zhang, N., Zhou, K.,and Li, D., Back-propagation neural network and support vector machines for gold mineral prospectivity mapping in the Hatu region, Xinjiang, China. Earth Sci Inform. 11(4), pp. 553-566, 2018. DOI: https://doi.org/10.1007/s12145-018-0346-6

[15] Mahvash-Mohammadi, N., and Hezarkhani, A., Application of support vector machine for the separation of mineralised zones in the Takht-e-Gonbad porphyry deposit, SE Iran. Journal of African Earth Sciences. 143, pp. 301-308, 2018. DOI: https://doi.org/10.1016/j.jafrearsci.2018.02.005

[16] Taboada, J., Matías, J.M., Ordóñez, C., and García, P.J., Creating a quality map of a slate deposit using support vector machines. J Comput Appl Math. 204(1), pp. 84-94, 2007. DOI: https://doi.org/10.1016/j.cam.2006.04.030

[17] Bonilla, G., Castaño, A., Nieto, M.A., and Parra, S., Guía de buenas prácticas de la esmeralda colombiana. Published online 2020.

[18] Platt, J.C., Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers. 10(3), pp. 61-74, 1999.

[19] Kursa, M., Jankowski, A., and Rudnicki, W., Boruta - A system for feature selection. Fundam Inform. 101, pp. 271-285, 2010. DOI: https://doi.org/10.3233/FI-2010-288

[20] Nguyen, H.B., Xue, B., Liu, I., and Zhang, M., Filter based backward elimination in wrapper based PSO for feature selection in classification. In: 2014 IEEE Congress on Evolutionary Computation (CEC). 2014, pp. 3111-3118. DOI: https://doi.org/10.1109/CEC.2014.6900657

[21] Kaplan, D., Bayesian statistics for the social sciences. The Guilford Press. 2014, 318 P.

[22] Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q., On Calibration of modern neural Networks. Proceedings of the 34th International Conference on Machine Learning. Vol. 70, 2017. DOI: https://doi.org/10.48550/ARXIV.1706.04599

[23] Niculescu-Mizil, A., and Caruana, R., Obtaining Calibrated probabilities from Boosting. In: UAI. Vol 5, 2005, pp. 413-420.

[24] Brier, G.W., Weather review verification of forecasts expressed in terms of probability. Monthy Weather Review. [online]. 78(1), pp. 1-3, 1950. [Accessed November 13th, 2023]. Available at: https://journals.ametsoc.org/view/journals/mwre/78/1/1520-0493_1950_078_0001_vofeit_2_0_co_2.xml. DOI: https://doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2

[25] Roulston, M.S., Performance targets and the Brier score. Meteorological Applications. 14(2), pp. 185-194, 2007. DOI: https://doi.org/10.1002/met.21

[26] Niu, L., A review of the application of logistic regression in educational research: common issues, implications, and suggestions. Educ Rev (Birm). 72(1), pp. 41-67, 2020. DOI: https://doi.org/10.1080/00131911.2018.1483892

[27] Kilkenny, M.F., and Robinson, K.M., Data quality: “Garbage in – garbage out.” Health Information Management Journal. 47(3), pp. 103-105, 2018. DOI: https://doi.org/10.1177/1833358318774357

[28] Burgess, J., Buxton, N., Dyck, D., and Oosterveld, M., Thurston M., CIM Estimation best practice committee & mineral reserves best practices guidelines. Guidelines Specific to Particular Commodities Rock Hosted Diamonds. CIM Estimation Best Practice Committee. Published online, 2008.

[29] Abu-Mostafa, Y.S., Magdon-Ismail, M., and Lin, H.-T., Learning from data, AMLBook.com., vol. 1. AMLBook.com, 2012.

Cómo citar

IEEE

[1]
D. Neva-Rodriguez y L. H. Ochoa-Gutierrez, «Estimation of emerald mineralization probability using machine learning algorithms», DYNA, vol. 92, n.º 235, pp. 19–27, ene. 2025.

ACM

[1]
Neva-Rodriguez, D. y Ochoa-Gutierrez, L.H. 2025. Estimation of emerald mineralization probability using machine learning algorithms. DYNA. 92, 235 (ene. 2025), 19–27. DOI:https://doi.org/10.15446/dyna.v92n235.112504.

ACS

(1)
Neva-Rodriguez, D.; Ochoa-Gutierrez, L. H. Estimation of emerald mineralization probability using machine learning algorithms. DYNA 2025, 92, 19-27.

APA

Neva-Rodriguez, D. y Ochoa-Gutierrez, L. H. (2025). Estimation of emerald mineralization probability using machine learning algorithms. DYNA, 92(235), 19–27. https://doi.org/10.15446/dyna.v92n235.112504

ABNT

NEVA-RODRIGUEZ, D.; OCHOA-GUTIERREZ, L. H. Estimation of emerald mineralization probability using machine learning algorithms. DYNA, [S. l.], v. 92, n. 235, p. 19–27, 2025. DOI: 10.15446/dyna.v92n235.112504. Disponível em: https://revistas.unal.edu.co/index.php/dyna/article/view/112504. Acesso em: 3 feb. 2025.

Chicago

Neva-Rodriguez, Daniela, y Luis Hernán Ochoa-Gutierrez. 2025. «Estimation of emerald mineralization probability using machine learning algorithms». DYNA 92 (235):19-27. https://doi.org/10.15446/dyna.v92n235.112504.

Harvard

Neva-Rodriguez, D. y Ochoa-Gutierrez, L. H. (2025) «Estimation of emerald mineralization probability using machine learning algorithms», DYNA, 92(235), pp. 19–27. doi: 10.15446/dyna.v92n235.112504.

MLA

Neva-Rodriguez, D., y L. H. Ochoa-Gutierrez. «Estimation of emerald mineralization probability using machine learning algorithms». DYNA, vol. 92, n.º 235, enero de 2025, pp. 19-27, doi:10.15446/dyna.v92n235.112504.

Turabian

Neva-Rodriguez, Daniela, y Luis Hernán Ochoa-Gutierrez. «Estimation of emerald mineralization probability using machine learning algorithms». DYNA 92, no. 235 (enero 27, 2025): 19–27. Accedido febrero 3, 2025. https://revistas.unal.edu.co/index.php/dyna/article/view/112504.

Vancouver

1.
Neva-Rodriguez D, Ochoa-Gutierrez LH. Estimation of emerald mineralization probability using machine learning algorithms. DYNA [Internet]. 27 de enero de 2025 [citado 3 de febrero de 2025];92(235):19-27. Disponible en: https://revistas.unal.edu.co/index.php/dyna/article/view/112504

Descargar cita

CrossRef Cited-by

CrossRef citations0

Dimensions

PlumX

Visitas a la página del resumen del artículo

16

Descargas