Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire
This study aimed to model the prospectivity for placer deposits using geomorphic and landscape parameters. Within a geographic information system (GIS), spatial autocorrelation analysis of 3709 geochemical samples was used to identify prospective and non-prospective targets for columbite-tantalite (...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/12/11/1453 |
| _version_ | 1797464520434647040 |
|---|---|
| author | Kassi Olivier Shaw Kalifa Goïta Mickaël Germain |
| author_facet | Kassi Olivier Shaw Kalifa Goïta Mickaël Germain |
| author_sort | Kassi Olivier Shaw |
| collection | DOAJ |
| description | This study aimed to model the prospectivity for placer deposits using geomorphic and landscape parameters. Within a geographic information system (GIS), spatial autocorrelation analysis of 3709 geochemical samples was used to identify prospective and non-prospective targets for columbite-tantalite (Nb-Ta) placer deposits of Hana-Lobo (H-L) Geological Complex (West- Central Côte d’Ivoire, West Africa). Based on mineralization system analysis, hydrologic, geomorphologic and landscape parameters were extracted at the locations of the identified targets. Supervised automatic classification approaches were applied, including Random Forest (RF), K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) to find a prospectivity model complex enough to capture the nature of the data. Metrics such as cross-validation accuracy (CVA), Receiver Operating Characteristic (ROC) curves, Area Under Curve (AUC) values and F-score values were used to evaluate the performance and robustness of output models. Results of applying machine-learning algorithms demonstrated that predictions provided by the final RF and KNN models were very close (<i>κ</i> = 0.56 and CVA = 0.69; <i>κ</i> = 0.54 and CVA = 0.68, respectively) and those provided by the SVM models were slightly lower with <i>κ</i> = 0.46 and CVA = 0.63. Independent validation results confirmed the slightly higher performance of both KNN and RF prospectivity models, compared to final SVM. Sensitivity analyses of both KNN and RF prospectivity models for medium and high-grade Nb-Ta deposits show a prediction rate of up to 90%. |
| first_indexed | 2024-03-09T18:08:20Z |
| format | Article |
| id | doaj.art-da07eb2e5c40460786557d6d9fd12820 |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-09T18:08:20Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-da07eb2e5c40460786557d6d9fd128202023-11-24T09:18:34ZengMDPI AGMinerals2075-163X2022-11-011211145310.3390/min12111453Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’IvoireKassi Olivier Shaw0Kalifa Goïta1Mickaël Germain2Center for Applications and Research in Remote Sensing (CARTEL), Department of Applied Geomatics, University of Sherbrooke, 2500 Boulevard de l’Université, Sherbrooke, QC J1K 2R1, CanadaCenter for Applications and Research in Remote Sensing (CARTEL), Department of Applied Geomatics, University of Sherbrooke, 2500 Boulevard de l’Université, Sherbrooke, QC J1K 2R1, CanadaCenter for Applications and Research in Remote Sensing (CARTEL), Department of Applied Geomatics, University of Sherbrooke, 2500 Boulevard de l’Université, Sherbrooke, QC J1K 2R1, CanadaThis study aimed to model the prospectivity for placer deposits using geomorphic and landscape parameters. Within a geographic information system (GIS), spatial autocorrelation analysis of 3709 geochemical samples was used to identify prospective and non-prospective targets for columbite-tantalite (Nb-Ta) placer deposits of Hana-Lobo (H-L) Geological Complex (West- Central Côte d’Ivoire, West Africa). Based on mineralization system analysis, hydrologic, geomorphologic and landscape parameters were extracted at the locations of the identified targets. Supervised automatic classification approaches were applied, including Random Forest (RF), K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) to find a prospectivity model complex enough to capture the nature of the data. Metrics such as cross-validation accuracy (CVA), Receiver Operating Characteristic (ROC) curves, Area Under Curve (AUC) values and F-score values were used to evaluate the performance and robustness of output models. Results of applying machine-learning algorithms demonstrated that predictions provided by the final RF and KNN models were very close (<i>κ</i> = 0.56 and CVA = 0.69; <i>κ</i> = 0.54 and CVA = 0.68, respectively) and those provided by the SVM models were slightly lower with <i>κ</i> = 0.46 and CVA = 0.63. Independent validation results confirmed the slightly higher performance of both KNN and RF prospectivity models, compared to final SVM. Sensitivity analyses of both KNN and RF prospectivity models for medium and high-grade Nb-Ta deposits show a prediction rate of up to 90%.https://www.mdpi.com/2075-163X/12/11/1453predictive mineral “prospectivity” mappingGISmachine-learning algorithmsmining explorationcolumbite-tantaliteIvory Coast |
| spellingShingle | Kassi Olivier Shaw Kalifa Goïta Mickaël Germain Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire Minerals predictive mineral “prospectivity” mapping GIS machine-learning algorithms mining exploration columbite-tantalite Ivory Coast |
| title | Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire |
| title_full | Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire |
| title_fullStr | Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire |
| title_full_unstemmed | Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire |
| title_short | Prospectivity Mapping of Heavy Mineral Ore Deposits Based upon Machine-Learning Algorithms: Columbite-Tantalite Deposits in West- Central Côte d’Ivoire |
| title_sort | prospectivity mapping of heavy mineral ore deposits based upon machine learning algorithms columbite tantalite deposits in west central cote d ivoire |
| topic | predictive mineral “prospectivity” mapping GIS machine-learning algorithms mining exploration columbite-tantalite Ivory Coast |
| url | https://www.mdpi.com/2075-163X/12/11/1453 |
| work_keys_str_mv | AT kassioliviershaw prospectivitymappingofheavymineraloredepositsbaseduponmachinelearningalgorithmscolumbitetantalitedepositsinwestcentralcotedivoire AT kalifagoita prospectivitymappingofheavymineraloredepositsbaseduponmachinelearningalgorithmscolumbitetantalitedepositsinwestcentralcotedivoire AT mickaelgermain prospectivitymappingofheavymineraloredepositsbaseduponmachinelearningalgorithmscolumbitetantalitedepositsinwestcentralcotedivoire |