Estimation of emerald mineralization probability using machine learning algorithms

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 varia...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniela Neva-Rodriguez, Luis Hernán Ochoa-Gutierrez
Format: Article
Language:English
Published: Universidad Nacional de Colombia 2025-01-01
Series:Dyna
Subjects:
Online Access:https://revistas.unal.edu.co/index.php/dyna/article/view/112504
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762019879682048
author Daniela Neva-Rodriguez
Luis Hernán Ochoa-Gutierrez
author_facet Daniela Neva-Rodriguez
Luis Hernán Ochoa-Gutierrez
author_sort Daniela Neva-Rodriguez
collection DOAJ
description 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.
format Article
id doaj-art-683b0c055c9a409aa0db754fbd5f422e
institution DOAJ
issn 0012-7353
2346-2183
language English
publishDate 2025-01-01
publisher Universidad Nacional de Colombia
record_format Article
series Dyna
spelling doaj-art-683b0c055c9a409aa0db754fbd5f422e2025-08-20T03:05:50ZengUniversidad Nacional de ColombiaDyna0012-73532346-21832025-01-019223510.15446/dyna.v92n235.112504Estimation of emerald mineralization probability using machine learning algorithmsDaniela Neva-Rodriguez0https://orcid.org/0009-0004-3254-4667Luis Hernán Ochoa-Gutierrez1https://orcid.org/0000-0002-3607-7339Universidad Nacional de Colombia, sede Bogotá, Facultad de Ciencias, Departamento de Geociencias, Bogotá, ColombiaUniversidad Nacional de Colombia, sede Bogotá, Facultad de Ciencias, Departamento de Geociencias, Bogotá, ColombiaThis 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. https://revistas.unal.edu.co/index.php/dyna/article/view/112504gemscalibrationdrillholemineral target
spellingShingle Daniela Neva-Rodriguez
Luis Hernán Ochoa-Gutierrez
Estimation of emerald mineralization probability using machine learning algorithms
Dyna
gems
calibration
drillhole
mineral target
title Estimation of emerald mineralization probability using machine learning algorithms
title_full Estimation of emerald mineralization probability using machine learning algorithms
title_fullStr Estimation of emerald mineralization probability using machine learning algorithms
title_full_unstemmed Estimation of emerald mineralization probability using machine learning algorithms
title_short Estimation of emerald mineralization probability using machine learning algorithms
title_sort estimation of emerald mineralization probability using machine learning algorithms
topic gems
calibration
drillhole
mineral target
url https://revistas.unal.edu.co/index.php/dyna/article/view/112504
work_keys_str_mv AT danielanevarodriguez estimationofemeraldmineralizationprobabilityusingmachinelearningalgorithms
AT luishernanochoagutierrez estimationofemeraldmineralizationprobabilityusingmachinelearningalgorithms