Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil
Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative data...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/12/8/941 |
| _version_ | 1797408692933492736 |
|---|---|
| author | Victor Silva dos Santos Erwan Gloaguen Vinicius Hector Abud Louro Martin Blouin |
| author_facet | Victor Silva dos Santos Erwan Gloaguen Vinicius Hector Abud Louro Martin Blouin |
| author_sort | Victor Silva dos Santos |
| collection | DOAJ |
| description | Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative datasets is required. As a result, techniques for selecting point locations to represent negative examples must be employed. Several approaches have been proposed in the past; however, one can never be certain that the points chosen are true negatives or, at the very least, optimal for training. As a consequence, methodologies that account for the uncertainty of the generation of negative datasets in MPM are needed. In this paper, we compare two criteria for selecting negative examples and quantify the uncertainty associated with this process by generating 400 potential maps for each of the three ML methods utilized (200 maps for each criterion), which include random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNC). The results showed that applying a geological constraint to the creation of negative datasets reduced prediction uncertainty and improved overall model performance but produced larger areas of very high probability (i.e., >0.9) when compared to using only the spatial distribution of known deposits and occurrences as a constraint. SHAP values were used to find approximations for the importance of features in nonlinear methods, and kernel density estimations were used to examine how they varied depending on the negative dataset used to train the ML models. Prospectivity models for magmatic-hydrothermal gold deposits were generated using data from the shuttle radar terrain mission, gamma-ray, magnetic lineaments, and proximity to dykes. The Juruena Mineral Province, situated in Northern Mato Grosso, Brazil, represented the case study for this work. |
| first_indexed | 2024-03-09T04:03:14Z |
| format | Article |
| id | doaj.art-1c802478088e40a7b86aab1b79dfced0 |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-09T04:03:14Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-1c802478088e40a7b86aab1b79dfced02023-12-03T14:10:02ZengMDPI AGMinerals2075-163X2022-07-0112894110.3390/min12080941Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, BrazilVictor Silva dos Santos0Erwan Gloaguen1Vinicius Hector Abud Louro2Martin Blouin3Centre Terre Eau Environnement, Institut National de la Recherche Scientifique, 490 Couronne St, Quebec City, QC G1K 9A9, CanadaCentre Terre Eau Environnement, Institut National de la Recherche Scientifique, 490 Couronne St, Quebec City, QC G1K 9A9, CanadaInstituto de Geociências, Universidade de São Paulo-USP, Rua do Lago 562, São Paulo 05508-080, BrazilCentre Terre Eau Environnement, Institut National de la Recherche Scientifique, 490 Couronne St, Quebec City, QC G1K 9A9, CanadaMineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative datasets is required. As a result, techniques for selecting point locations to represent negative examples must be employed. Several approaches have been proposed in the past; however, one can never be certain that the points chosen are true negatives or, at the very least, optimal for training. As a consequence, methodologies that account for the uncertainty of the generation of negative datasets in MPM are needed. In this paper, we compare two criteria for selecting negative examples and quantify the uncertainty associated with this process by generating 400 potential maps for each of the three ML methods utilized (200 maps for each criterion), which include random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNC). The results showed that applying a geological constraint to the creation of negative datasets reduced prediction uncertainty and improved overall model performance but produced larger areas of very high probability (i.e., >0.9) when compared to using only the spatial distribution of known deposits and occurrences as a constraint. SHAP values were used to find approximations for the importance of features in nonlinear methods, and kernel density estimations were used to examine how they varied depending on the negative dataset used to train the ML models. Prospectivity models for magmatic-hydrothermal gold deposits were generated using data from the shuttle radar terrain mission, gamma-ray, magnetic lineaments, and proximity to dykes. The Juruena Mineral Province, situated in Northern Mato Grosso, Brazil, represented the case study for this work.https://www.mdpi.com/2075-163X/12/8/941mineral prospectivity mappingmachine learningquantification of uncertaintydata integrationJuruena Mineral Province |
| spellingShingle | Victor Silva dos Santos Erwan Gloaguen Vinicius Hector Abud Louro Martin Blouin Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil Minerals mineral prospectivity mapping machine learning quantification of uncertainty data integration Juruena Mineral Province |
| title | Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil |
| title_full | Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil |
| title_fullStr | Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil |
| title_full_unstemmed | Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil |
| title_short | Machine Learning Methods for Quantifying Uncertainty in Prospectivity Mapping of Magmatic-Hydrothermal Gold Deposits: A Case Study from Juruena Mineral Province, Northern Mato Grosso, Brazil |
| title_sort | machine learning methods for quantifying uncertainty in prospectivity mapping of magmatic hydrothermal gold deposits a case study from juruena mineral province northern mato grosso brazil |
| topic | mineral prospectivity mapping machine learning quantification of uncertainty data integration Juruena Mineral Province |
| url | https://www.mdpi.com/2075-163X/12/8/941 |
| work_keys_str_mv | AT victorsilvadossantos machinelearningmethodsforquantifyinguncertaintyinprospectivitymappingofmagmatichydrothermalgolddepositsacasestudyfromjuruenamineralprovincenorthernmatogrossobrazil AT erwangloaguen machinelearningmethodsforquantifyinguncertaintyinprospectivitymappingofmagmatichydrothermalgolddepositsacasestudyfromjuruenamineralprovincenorthernmatogrossobrazil AT viniciushectorabudlouro machinelearningmethodsforquantifyinguncertaintyinprospectivitymappingofmagmatichydrothermalgolddepositsacasestudyfromjuruenamineralprovincenorthernmatogrossobrazil AT martinblouin machinelearningmethodsforquantifyinguncertaintyinprospectivitymappingofmagmatichydrothermalgolddepositsacasestudyfromjuruenamineralprovincenorthernmatogrossobrazil |