Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador
Mineral exploration campaigns are financially risky. Several state-of-the-art methods have been developed to mitigate the risk, including predictive modelling of mineral prospectivity using principal component analysis (PCA) and geographic information systems (GIS). The PCA and GIS approach is curre...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2021-12-01
|
| Series: | Artificial Intelligence in Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666544122000028 |
| _version_ | 1811155476692336640 |
|---|---|
| author | Steven E. Zhang Julie E. Bourdeau Glen T. Nwaila David Corrigan |
| author_facet | Steven E. Zhang Julie E. Bourdeau Glen T. Nwaila David Corrigan |
| author_sort | Steven E. Zhang |
| collection | DOAJ |
| description | Mineral exploration campaigns are financially risky. Several state-of-the-art methods have been developed to mitigate the risk, including predictive modelling of mineral prospectivity using principal component analysis (PCA) and geographic information systems (GIS). The PCA and GIS approach is currently considered acceptable for generating mineral exploration targets. However, some of its limitations are the dependence on sample stoichiometry (e.g., the existence of minerals), the necessity of log-ratio transformations when dealing with compositional data, and manual interpretation and use of principal components to enhance potential geochemical anomalies for prospectivity mapping. In this study, we generalize the fundamental ideas behind the PCA and GIS approach by developing a new data-driven approach using ML. We showcase a new workflow capable of generating either intermediate evidence layers or final prospectivity maps that depict major regional geochemical anomalies using multi-element geochemical data from Southeastern Churchill Province (Québec and Labrador), Canada. The region is known for its REEs endowment and the data were gathered for prospectivity mapping. A comparison with the established multivariate hybrid data- and knowledge-based approach revealed that on a roughly comparable basis of the amount of manual effort, our new data-driven procedure can much more accurately identify geochemical anomalies in both univariate and multivariate applications. The results of our prospectivity mapping corroborate with the ground truth or known geological anomalies in the studied region. These findings have potentially wider implications on exploration target generation, where project risks (financial, environmental, political, etc.) and geochemical anomalies must be quantified using robust and effective data-driven approaches. In addition, our methodology is more replicable and objective, as manual geoscientific interpretation is not required during the detection of geochemical anomalies. |
| first_indexed | 2024-04-10T04:34:46Z |
| format | Article |
| id | doaj.art-2ff3b62c3ea9487e9d7d9b36193109af |
| institution | Directory Open Access Journal |
| issn | 2666-5441 |
| language | English |
| last_indexed | 2024-04-10T04:34:46Z |
| publishDate | 2021-12-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Geosciences |
| spelling | doaj.art-2ff3b62c3ea9487e9d7d9b36193109af2023-03-10T04:36:24ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412021-12-012128147Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and LabradorSteven E. Zhang0Julie E. Bourdeau1Glen T. Nwaila2David Corrigan3SmartMin Limited, 39 Kiewiet Street, Helikon Park, 1759, South AfricaGeological Survey of Canada, 601 Booth Street, Ottawa, Ontario, K1A 0E8, CanadaSchool of Geosciences, University of the Witwatersrand, 1 Jan Smuts Ave, Johannesburg, 2000, South Africa; Corresponding author.79 Lynn Street, Gatineau, Québec, J9H 1B5, CanadaMineral exploration campaigns are financially risky. Several state-of-the-art methods have been developed to mitigate the risk, including predictive modelling of mineral prospectivity using principal component analysis (PCA) and geographic information systems (GIS). The PCA and GIS approach is currently considered acceptable for generating mineral exploration targets. However, some of its limitations are the dependence on sample stoichiometry (e.g., the existence of minerals), the necessity of log-ratio transformations when dealing with compositional data, and manual interpretation and use of principal components to enhance potential geochemical anomalies for prospectivity mapping. In this study, we generalize the fundamental ideas behind the PCA and GIS approach by developing a new data-driven approach using ML. We showcase a new workflow capable of generating either intermediate evidence layers or final prospectivity maps that depict major regional geochemical anomalies using multi-element geochemical data from Southeastern Churchill Province (Québec and Labrador), Canada. The region is known for its REEs endowment and the data were gathered for prospectivity mapping. A comparison with the established multivariate hybrid data- and knowledge-based approach revealed that on a roughly comparable basis of the amount of manual effort, our new data-driven procedure can much more accurately identify geochemical anomalies in both univariate and multivariate applications. The results of our prospectivity mapping corroborate with the ground truth or known geological anomalies in the studied region. These findings have potentially wider implications on exploration target generation, where project risks (financial, environmental, political, etc.) and geochemical anomalies must be quantified using robust and effective data-driven approaches. In addition, our methodology is more replicable and objective, as manual geoscientific interpretation is not required during the detection of geochemical anomalies.http://www.sciencedirect.com/science/article/pii/S2666544122000028MLMineral prospectivity mappingPrincipal component analysisGeochemical anomalyREEs |
| spellingShingle | Steven E. Zhang Julie E. Bourdeau Glen T. Nwaila David Corrigan Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador Artificial Intelligence in Geosciences ML Mineral prospectivity mapping Principal component analysis Geochemical anomaly REEs |
| title | Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador |
| title_full | Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador |
| title_fullStr | Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador |
| title_full_unstemmed | Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador |
| title_short | Towards a fully data-driven prospectivity mapping methodology: A case study of the Southeastern Churchill Province, Québec and Labrador |
| title_sort | towards a fully data driven prospectivity mapping methodology a case study of the southeastern churchill province quebec and labrador |
| topic | ML Mineral prospectivity mapping Principal component analysis Geochemical anomaly REEs |
| url | http://www.sciencedirect.com/science/article/pii/S2666544122000028 |
| work_keys_str_mv | AT stevenezhang towardsafullydatadrivenprospectivitymappingmethodologyacasestudyofthesoutheasternchurchillprovincequebecandlabrador AT julieebourdeau towardsafullydatadrivenprospectivitymappingmethodologyacasestudyofthesoutheasternchurchillprovincequebecandlabrador AT glentnwaila towardsafullydatadrivenprospectivitymappingmethodologyacasestudyofthesoutheasternchurchillprovincequebecandlabrador AT davidcorrigan towardsafullydatadrivenprospectivitymappingmethodologyacasestudyofthesoutheasternchurchillprovincequebecandlabrador |