Transforming LCT Pegmatite Targeting Models into AI-Powered Predictive Maps of Lithium Potential for Western Australia and Ontario: Approach, Results and Implications
Preprint
- 12 February 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Lithium-cesium-tantalum (LCT) pegmatites account for circa one-third of global lithium resources and two-thirds of global lithium production. Western Australia, the world's largest supplier of hardrock lithium ores, and Ontario, an emerging lithium mining jurisdiction, have significant endowments that will be critical to the ‘green revolution’ given the predicted transition to lithium-based electromobility. In addition, both jurisdictions show excellent potential for future lithium discoveries given they cover large areas of favorable geology that, by and large, have recorded only limited lithium exploration. Here, we developed holistic LCT pegmatite targeting models for these important jurisdictions, informed by a detailed review of this deposit type and framed in the context of a mineral systems approach. Artificial intelligence (AI)-powered mineral potential modelling (MPM), using multiple, complimentary techniques and guided by the mappable elements of the LCT pegmatite genetic model, not only delivered the first regional scale views of lithium potential across the Archean to Proterozoic terrains of Western Australia and Ontario but also delivered compelling targets for future exploration and though-provoking insights, such as the statistically verifiable proximity relationship between lithium, gold and nickel occurrences. Overall, this study also served to demonstrate the power of precompetitive, high-quality geoscience data, not only for regional scale targeting but also the development of camp-scale targets that are concise enough to be investigated using conventional prospecting techniques.Keywords
All Related Versions
This publication has 57 references indexed in Scilit:
- Artificial intelligence for mineral exploration: A review and perspectives on future directions from data scienceEarth-Science Reviews, 2024
- BWM-SAW: A new hybrid MCDM technique for modeling of chromite potential in the Birjand district, east of IranJournal of Geochemical Exploration, 2021
- Cuckoo optimization algorithm for support vector regression potential analysis: An example from the Granites-Tanami Orogen, AustraliaJournal of Geochemical Exploration, 2021
- A data augmentation approach to XGboost-based mineral potential mapping: An example of carbonate-hosted Zn Pb mineral systems of Western IranJournal of Geochemical Exploration, 2021
- Mineral Prospectivity Mapping based on Isolation Forest and Random Forest: Implication for the Existence of Spatial Signature of Mineralization in OutliersNatural Resources Research, 2021
- FUCOM-MOORA and FUCOM-MOOSRA: new MCDM-based knowledge-driven procedures for mineral potential mapping in greenfieldsSN Applied Sciences, 2021
- 3D Mineral Prospectivity Mapping with Random Forests: A Case Study of Tongling, Anhui, ChinaNatural Resources Research, 2019
- An Improved Prediction-Area Plot for Prospectivity Analysis of Mineral DepositsNatural Resources Research, 2018
- Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mappingJournal of Geochemical Exploration, 2016
- Data-Driven Index Overlay and Boolean Logic Mineral Prospectivity Modeling in Greenfields ExplorationNatural Resources Research, 2015